Publications

@inproceedings{gao2025syncdiff,
 author = {Heting Gao and Xulin Fan and Mark Hasegawa-Johnson},
 booktitle = {WACV Winter Conference on Applications of Computer Vision},
 month = {3},
 title = {SyncDiff: Diffusion-based Talking Head Synthesis with Bottlenecked Temporal Visual Prior for Improved Synchronization},
 url = {https://wacv2025.thecvf.com/},
 year = {2025}
}

@inproceedings{yoon2025can,
 author = {Eunseop Yoon and Heesuk Yoon and Mark Hasegawa-Johnson and Changdong Yoo},
 booktitle = {Proc. International Conference on Learning Representations (ICLR)},
 title = {Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models},
 year = {2025}
}

@inproceedings{na2025cohort,
 author = {Jonghwan Na and Mark Hasegawa-Johnson and Bowon Lee},
 booktitle = {Proc. ICASSP},
 title = {Cohort-Sensitive Labeling: An Effective Approach for Enhancing ASR Performance},
 year = {2025}
}

@inproceedings{na2025improved,
 author = {Jonghwan Na and Xiuwen Zheng and Mark Hasegawa-Johnson and Bowon Lee},
 booktitle = {Proc. ICASSP},
 title = {Improved Recognition of the Speech of People with Parkinson’s who Stutter},
 year = {2025}
}

@inproceedings{singh2025robust,
 author = {Satwinder Singh and Qianli Wang and Zihan Zhong and Clarion Mendes and Mark Hasegawa-Johnson and Waleed Abdulla and Seyed Reza Shahamiri},
 booktitle = {Proc. ICASSP},
 title = {Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition},
 year = {2025}
}

@inproceedings{wang2025robust,
 author = {Qianli Wang and Zihan Zong and Satwinder Singh and Clarion Mendes and Mark Hasegawa-Johnson and Waleed Abdulla and Seyed Reza Shahamiri},
 booktitle = {Proc. ICASSP},
 title = {Dysarthric Speech Conformer: Adaptation for Sequence-to-Sequence Dysarthric Speech Recognition},
 year = {2025}
}

@inproceedings{jahan2025unveiling,
 author = {Maliha Jahan and Priyam Mazumdar and Thomas Thebaud and Mark Hasegawa-Johnson and Jesus Villalba and Najim Dehak and Laureano Moro-Velazquez},
 booktitle = {Proc. ICASSP},
 title = {Unveiling Performance Bias in ASR Systems: A Study on Gender, Age, Accent, and More},
 year = {2025}
}

@inproceedings{singh2024comprehensive,
 author = {Satwinder Singh and Zihan Zhong and Qianli Wang and Clarion Mendes and Mark Hasegawa-Johnson and Waleed Abdulla and Seyed Reza Shahamiri},
 booktitle = {International Conference on Neural Information Processing (ICONIP2024)},
 month = {12},
 title = {A Comprehensive Performance Evaluation of Whisper Models in Dysarthric Speech Recognition},
 url = {https://iconip2024.org/},
 year = {2024}
}

@inproceedings{kim2024overview,
 author = {Heejin Kim and Clarion Mendes and Mark Hasegawa-Johnson and Meg Dickinson and Erik Hege},
 booktitle = {American Speech Language Hearing Association (ASHA) Annual Convention},
 month = {12},
 note = {unpublished presentation},
 title = {An Overview of Speech Data in the Speech Accessibility Project: Speech Variations for Inclusive Technology},
 url = {https://convention.asha.org/},
 year = {2024}
}

@inproceedings{wu2024just,
 author = {Junkai Wu and Xulin Fan and Bo-Ru Lu and Xilin Jiang and Nima Mesgarani and Mark Hasegawa-Johnson and Mari Ostendorf},
 booktitle = {IEEE Spoken Language Technology (SLT)},
 month = {12},
 title = {Just ASR + LLM? A Study on Speech Large Language Models’ Ability to Identify and Understand Speaker in Spoken Dialogue},
 url = {https://arxiv.org/abs/2409.04927},
 year = {2024}
}

@article{morshed2024using,
 author = {Mahir Morshed and Mark Hasegawa-Johnson},
 doi = {10.1121/10.0034415},
 journal = {J. Acoust. Soc. Am.},
 month = {11},
 number = {5},
 pages = {3411--3421},
 title = {Using Articulatory Feature Detectors in Progressive Networks for Multilingual Low-Resource Phone Recognition},
 url = {https://pubs.aip.org/asa/jasa/article/156/5/3411/3321345/Using-articulatory-feature-detectors-in},
 volume = {156},
 year = {2024}
}

@unpublished{le2024you,
 author = {Giang Le and Yinglun Sun and Maliha Jahan and Helin Wang and Thomas Thebaud and Zsuzsanna Fagyal and Mark Hasegawa-Johnson and Laureano Moro-Velazquez and Najim Dehak},
 month = {11},
 note = {presented at NWAV New Ways of Analyzing Variation},
 title = {"You are what, Chinese?" Modeling identifications of race, ethnicity, and national origin as stancetaking in a large podcast corpus of American English},
 year = {2024}
}

@inproceedings{khan2024infantmotion2vec,
 author = {Mohammad Nur Hossain Khan and Nancy McElwain and Mark Hasegawa-Johnson and Bashima Islam},
 booktitle = {IEEE International Conference on Wearable and Implantable Body Sensor Networks (BSN 2024)},
 month = {10},
 title = {InfantMotion2Vec: Unlabeled Data-Driven Infant Pose Estimation Using a Single Chest IMU},
 url = {https://bsn.embs.org/2024/},
 year = {2024}
}

@inproceedings{li2024enhancing,
 author = {Jialu Li and Mark Hasegawa-Johnson and Karrie Karahalios},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2024-540},
 month = {9},
 title = {Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis},
 year = {2024}
}

@inproceedings{yoon2024litta,
 author = {Eunseop Yoon and Hee Suk Yoon and John Harvill and Mark Hasegawa-Johnson and Chang D. Yoo},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2024-1829},
 month = {9},
 title = {LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition},
 year = {2024}
}

@inproceedings{zheng2024fine,
 author = {Xiuwen Zheng and Bornali Phukon and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2024-1969},
 month = {9},
 title = {Fine-Tuning Automatic Speech Recognition for People with Parkinson's: An Effective Strategy for Enhancing Speech Technology Accessibility},
 year = {2024}
}

@inproceedings{gao2024speech,
 author = {Heting Gao and Kaizhi Qian and Junrui Ni and Chuang Gan and Mark A. Hasegawa-Johnson and
Shiyu Chang and Yang Zhang},
 booktitle = {Proc. International Conference on Machine Learning (ICML)},
 month = {7},
 title = {Speech Self-Supervised Learning Using Diffusion Model Synthetic Data},
 url = {https://openreview.net/forum?id=ecnpYYHjt9},
 year = {2024}
}

@inproceedings{hu2024real2,
 author = {Yannan Hu and Nancy L. McElwain and Mark Hasegawa-Johnson},
 booktitle = {Speech Prosody},
 doi = {10.21437/SpeechProsody.2024-45},
 month = {7},
 pages = {accepted for publication},
 title = {Real-Time Relations Between Prosodic Features of Infant-Directed Speech and Infant Attention at 3 Months},
 year = {2024}
}

@inproceedings{hu2024real,
 address = {Glasgow, Scotland},
 author = {Yannan Hu and Nancy L. McElwain and Mark Hasegawa-Johnson},
 booktitle = {24th International Congress of Infant Studies (ICIS)},
 month = {July},
 note = {Poster presentation},
 title = {Real-time relations between fundamental frequency of infant-directed speech and infant attention at 3 months},
 year = {2024}
}

@inproceedings{jahan2024finding,
 author = {Maliha Jahan and Helin Wang and Thomas Thebaud and Yinglun Sun and Giang Le and Zsuzsanna Fagyal and Odette Scharenborg and Mark Hasegawa-Johnson and Laureano Moro Velazquez and Najim Dehak},
 booktitle = {LREC-COLING},
 month = {5},
 pages = {7296-7306},
 title = {Finding Spoken Identifications: Using GPT-4 Annotation For An Efficient And Fast Dataset Creation Pipeline},
 url = {https://aclanthology.org/2024.lrec-main.641/},
 year = {2024}
}

@inproceedings{yoon2024calibrated,
 author = {Hee Suk Yoon and Eunseop Yoon and Joshua Tian Jin Tee and Mark A. Hasegawa-Johnson
and Yingzhen Li and Chang D. Yoo},
 booktitle = {Proc. International Conference on Learning Representations (ICLR)},
 month = {5},
 title = {C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion},
 url = {https://iclr.cc/virtual/2024/poster/17996},
 year = {2024}
}

@phdthesis{harvill2024speech,
 author = {John Harvill},
 keywords = {recognition},
 month = {April},
 school = {University of Illinois},
 title = {Speech classification and lexical semantic modeling via self-supervision and knowledge transfer},
 url = {https://www.ideals.illinois.edu/items/131435},
 year = {2024}
}

@article{singh2024lightweight,
 author = {Abhayjeet Singh and Amala Nagireddi and Anjali Jayakumar and Deekshitha G and Jesuraja Bandekar and Roopa R and Sandhya Badiger and Sathvik Udupa and Saurabh Kumar and Prasanta Kumar Ghosh and Hema A Murthy and Heiga Zen and Pranaw Kumar and Kamal Kant and Amol Bole and Bira Chandra Singh and Keiichi Tokuda and Mark Hasegawa-Johnson and Philipp Olbrich},
 doi = {10.1109/OJSP.2024.3379092},
 issn = {2644-1322},
 journal = {IEEE Open Journal of Signal Processing},
 month = {3},
 pages = {790--798},
 title = {Lightweight, Multi-speaker, Multi-lingual Indic Text-To-Speech},
 url = {https://ieeexplore.ieee.org/document/10479171?source=authoralert},
 volume = {5},
 year = {2024}
}

@phdthesis{gao2024unsupervised,
 author = {Heting Gao},
 keywords = {recognition},
 month = {March},
 school = {University of Illinois},
 title = {Unsupervised speech technology for low-resource languages},
 url = {https://www.ideals.illinois.edu/items/131276},
 year = {2024}
}

@phdthesis{li2024breaking,
 author = {Jialu Li},
 keywords = {biomedical},
 month = {March},
 school = {University of Illinois},
 title = {Breaking down barriers: advancing interdisciplinary speech applications in early children’s development},
 url = {https://www.ideals.illinois.edu/items/131512},
 year = {2024}
}

@phdthesis{wang2024reasoning,
 author = {Zhonghao Wang},
 keywords = {vision},
 month = {March},
 school = {University of Illinois},
 title = {Reasoning, scaling, generating with vision-language models},
 url = {https://www.ideals.illinois.edu/items/131362},
 year = {2024}
}

@article{islam2024preliminary,
 author = {Bashima Islam and Nancy L McElwain and Jialu Li and Maria Davila and Yannan Hu and Kexin Hu and Jordan M Bodway and Ashutosh M Dhekne and Romit Roy Choudhury and Mark Hasegawa-Johnson},
 doi = {https://www.mdpi.com/1424-8220/24/3/901},
 journal = {Sensors},
 month = {1},
 number = {3},
 title = {Preliminary Technical Validation of LittleBeats™: A Multimodal Sensing Platform to Capture Cardiac Physiology, Motion, and Vocalizations},
 volume = {24},
 year = {2024}
}

@article{hasegawajohnson2024community,
 author = {Mark Hasegawa-Johnson and Xiuwen Zheng and Heejin Kim and Clarion Mendes and Meg Dickinson and Erik Hege and Chris Zwilling and Marie Moore Channell and Laura Mattie and Heather Hodges and Lorraine Ramig and Mary Bellard and Mike Shebanek and Leda Sarı and Kaustubh Kalgaonkar and David Frerichs and Jeffrey P. Bigham and Leah Findlater and Colin Lea and Sarah Herrlinger and Peter Korn and Shadi Abou-Zahra and Rus Heywood and Katrin Tomanek and Bob MacDonald},
 doi = {10.1044/2024_JSLHR-24-00122},
 journal = {Journal of Speech Language and Hearing Research},
 number = {10},
 pages = {4162-4175},
 title = {Community-supported shared infrastructure in support of speech accessibility},
 url = {https://pubs.asha.org/doi/10.1044/2024_JSLHR-24-00122},
 volume = {67},
 year = {2024}
}

@article{harvill2024multimodal,
 author = {John Harvill and Moitreya Chatterjee and Shaveta Khosla and Mustafa Alam and Narendra Ahuja
and Mark Hasegawa-Johnson and David Chestek and David Beiser},
 doi = {10.1109/JTEHM.2024.3418345},
 issn = {2168-2372},
 journal = {IEEE Journal of Translational Engineering in Health and Medicine},
 title = {Multimodal Respiratory Rate Estimation from Audio and Video in Emergency Department Patients},
 url = {https://ieeexplore.ieee.org/document/10570324},
 year = {2024}
}

@inproceedings{wang2024unsupervised,
 author = {Liming Wang and Mark Hasegawa-Johnson and Chang Yoo},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP48485.2024.10446327},
 number = {4604},
 title = {Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching},
 year = {2024}
}

@inproceedings{gao2024g2pu,
 author = {Heting Gao and Mark Hasegawa-Johnson and Chang D. Yoo},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP48485.2024.10448105},
 number = {1746},
 title = {G2PU: Grapheme-to-Phoneme Transducer with Speech Units},
 year = {2024}
}

@article{mcelwain2024evaluating,
 author = {Nancy McElwain and Bashima Islam and Meghan Fisher and Camille Nebeker and Jordan Marie Bodway and Mark Hasegawa-Johnson},
 doi = {10.2196/49316},
 journal = {JMIR Human Factors},
 pages = {e49316},
 publisher = {JMIR Publications Toronto, Canada},
 title = {Evaluating Users’ Experiences of a Child Multimodal Wearable Device: A Mixed Methods Approach},
 volume = {11},
 year = {2024}
}

@article{azevedo2024influence,
 author = {Renato Azevedo and Rocio Garcia-Retamero and Mark Hasegawa-Johnson and Kuangxiao Gu and Danel G. Morrow},
 journal = {Human Factors in Healthcare},
 month = {12},
 pages = {100058},
 publisher = {Elsevier},
 title = {The Influence of Memory for and Affective Response to Health Messages on Self-care Behavioral Intentions},
 volume = {4},
 year = {2023}
}

@mastersthesis{zhang2024end,
 author = {Feiyu Zhang},
 school = {University of Illinois},
 title = {End-to-end modeling for code-switching automatic speech recognition},
 url = {https://www.ideals.illinois.edu/items/131716},
 year = {2024}
}

@mastersthesis{chang2024fusing,
 author = {Kai Chieh Chang},
 school = {University of Illinois},
 title = {Fusing multimodal neural networks: a study on sleep classification and sound event localization and detection},
 url = {https://www.ideals.illinois.edu/items/131693},
 year = {2024}
}

@inproceedings{chang2023classification,
 author = {Kai Chieh Chang and Mark Hasegawa-Johnson and Nancy L. McElwain and Bashima Islam},
 booktitle = {APSIPA ASC},
 keywords = {multimodal signal understanding},
 month = {11},
 title = {Classification of Infant Sleep/Wake States: Cross-Attention Among Large Scale Pretrained Transformer Networks Using Audio, ECG, and IMU Data},
 url = {https://arxiv.org/abs/2306.15808},
 year = {2023}
}

@inproceedings{wang2023a,
 author = {Liming Wang and Mark Hasegawa-Johnson and Chang D. Yoo},
 booktitle = {ACL},
 keywords = {recognition},
 month = {7},
 title = {A Theory of Unsupervised Speech Recognition},
 url = {https://arxiv.org/abs/2306.07926},
 year = {2023}
}

@inproceedings{wang2023speak,
 author = {Liming Wang and Junrui Ni and Heting Gao and Jialu Li and Kai Chieh Chang and Xulin Fan and Junkai Wu and Mark Hasegawa-Johnson and Chang D. Yoo},
 booktitle = {Findings of ACL},
 keywords = {recognition},
 month = {7},
 title = {Speak and Decipher and Sign: Toward Unsupervised Speech-to-Sign Language Recognition},
 url = {https://aclanthology.org/2023.findings-acl.424/},
 year = {2023}
}

@phdthesis{thomas2023evolution,
 author = {Oshane Odane Thomas},
 keywords = {biomedical},
 month = {June},
 school = {University of Illinois},
 title = {Evolution of primate cuboid form and the application of learning methods to the analysis of morphological and behavioral phenotypes},
 url = {https://www.ideals.illinois.edu/items/129109},
 year = {2023}
}

@phdthesis{wang2023multimodal,
 author = {Liming Wang},
 keywords = {recognition},
 month = {May},
 school = {University of Illinois},
 title = {Multimodal spoken unit discovery with paired and unpaired modalities},
 url = {https://www.ideals.illinois.edu/items/128694},
 year = {2023}
}

@article{cos2023importance,
 author = {Eugene Cox and Mark Hasegawa-Johnson and Suma Bhat and Mukhil Umashankar and H Chad Lane and Daniel Morrow},
 journal = {Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care},
 month = {3},
 number = {1},
 pages = {35--39},
 publisher = {SAGE Publications},
 title = {The Importance of Diverse User Goals When Designing an Automated COVID Risk Counselor},
 url = {https://journals.sagepub.com/doi/pdf/10.1177/2327857923121009},
 volume = {12},
 year = {2023}
}

@unpublished{hasegawajohnson2023community,
 author = {Mark Hasegawa-Johnson and Heejin Kim and Xiuwen Zheng and Meg Dickinson and Erik Hege and Clarion Mendes and Chris Zwilling and Shadi Abou-Zahra and Leah Findlater and Aaron Gustafson and Bob MacDonald and Mike Shebanek and Adina Bradshaw and Shawnise Carter and Blair Casey and Marie Moore Channell and Kayla Ferguson and Heather Hodges and Laura Mattie and Lorraine Ramig},
 note = {Unpublished presentation at the ASHA 2023 Research Symposium},
 number = {11},
 title = {Community-supported shared infrastructure in support of speech accessibility},
 url = {https://vimeo.com/911627521},
 volume = {67},
 year = {2023}
}

@inproceedings{li2023towards,
 author = {Jialu Li and Mark Hasegawa-Johnson and Nancy McElwain},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2023-460},
 keywords = {analysis},
 title = {Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio},
 url = {https://arxiv.org/abs/2305.12530},
 year = {2023}
}

@inproceedings{zhai2023wav2tobi,
 author = {Wanyue Zhai and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2023-477},
 keywords = {analysis},
 title = {Wav2ToBI: a new approach to automatic ToBI transcription},
 year = {2023}
}

@inproceedings{chang2023classification,
 author = {Chang, Kai Chieh and Hasegawa-Johnson, Mark and McElwain, Nancy L and Islam, Bashima},
 booktitle = {2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)},
 doi = {10.1109/APSIPAASC58517.2023.10317201},
 organization = {IEEE},
 pages = {2370--2377},
 title = {Classification of infant sleep/wake states: cross-attention among large scale pretrained transformer networks using audio, ECG, and IMU data},
 url = {https://ieeexplore.ieee.org/iel7/10317071/10317095/10317201.pdf},
 year = {2023}
}

@inproceedings{yoon2022smsmix,
 author = {Hee Suk Yoon and Eunseop Yoon and John Harvill and Sunjae Yoon and Mark Hasegawa-Johnson and Chang D. Yoo},
 booktitle = {EMNLP},
 keywords = {intelligence},
 month = {12},
 pages = {1493–1502},
 title = {SMSMix: Sense Maintained Sentence Mixup for Word Sense Disambiguation},
 url = {https://aclanthology.org/2022.findings-emnlp.107.pdf},
 year = {2022}
}

@inproceedings{yoon2023mitigating,
 author = {Eunseop Yoon and Hee Suk Yoon and Dhananjaya Gowda and SooHwan Eom and Daehyeok Kim and John Harvill and Heting Gao and Mark Hasegawa-Johnson and Chanwoo Kim and Chang D. Yoo},
 booktitle = {Proc. Interspeech},
 keywords = {recognition},
 title = {Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction},
 year = {2023}
}

@inproceedings{xu2023dual,
 author = {Zhongweiyang Xu and Xulin Fan and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of ICASSP},
 doi = {10.1109/ICASSP49357.2023.10096732},
 keywords = {recognition},
 note = {Recognized as one of the top 3% of papers at the conference},
 title = {Dual-Path Cross-Modal Attention for better Audio-Visual Speech Extraction},
 url = {https://drive.google.com/file/d/1IHK4EWuOiBX11fA7mdzUHIhCWK5ahOwf/view},
 year = {2023}
}

@inproceedings{kang2023end,
 author = {Wonjune Kang and Mark Hasegawa-Johnson and Deb Roy},
 booktitle = {Proc. Interspeech},
 keywords = {synthesis},
 title = {End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions},
 year = {2023}
}

@mastersthesis{lee2023explainable,
 author = {Seunghyun Lee},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Explainable artificial intelligence for inclusive automatic speech recognition},
 url = {https://www.ideals.illinois.edu/items/128583},
 year = {2023}
}

@article{zelasko2021discovering,
 author = {Piotr Zelasko and Siyuan Feng and Laureano Moro-Velazquez and Ali Abavisani and Saurabchand Bhati and Odette Scharenborg and Mark Hasegawa-Johnson and Najim Dehak},
 doi = {10.1016/j.csl.2022.101358},
 journal = {Computer Speech and Language},
 keywords = {recognition},
 month = {7},
 pages = {101358:1-54},
 title = {Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition},
 volume = {74},
 year = {2022}
}

@inproceedings{kang2022forget,
 author = {Haeyong Kang and Rusty John Lloyd Mina and Sultan Rizky Hikmawan Madjid and Jaehong Yoon and Mark Hasegawa-Johnson and Sung Ju Hwang and Chang D Yoo},
 booktitle = {Proc. International Conference on Machine Learning (ICML)},
 month = {6},
 pages = {10734-10750},
 title = {Forget-free continual learning with winning subnetworks},
 url = {https://proceedings.mlr.press/v162/kang22b.html},
 volume = {162},
 year = {2022}
}

@article{li2022autosegmental,
 author = {Jialu Li and Mark Hasegawa-Johnson},
 doi = {10.1109/TASLP.2022.3178238},
 journal = {IEEE Transactions on Audio, Speech and Language},
 keywords = {recognition},
 month = {5},
 pages = {1918-1926},
 title = {Autosegmental Neural Nets 2.0: An Extensive Study of Training Synchronous and Asynchronous Phones and Tones for Under-Resourced Tonal Languages},
 url = {https://ieeexplore.ieee.org/abstract/document/9783062},
 volume = {30},
 year = {2022}
}

@inproceedings{wang2022self,
 author = {Liming Wang and Siyuan Feng and Mark A. Hasegawa-Johnson and Chang D. Yoo},
 booktitle = {ACL},
 doi = {10.18653/v1/2022.acl-long.553},
 keywords = {recognition},
 month = {5},
 pages = {8027–8047},
 title = {Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition},
 year = {2022}
}

@phdthesis{abavisani2022role,
 author = {Ali Abavisani},
 keywords = {recognition},
 month = {May},
 school = {University of Illinois},
 title = {The role of talker change, vowel change and speech perceptual measure in hearing impaired phone recognition},
 url = {https://www.ideals.illinois.edu/items/125380},
 year = {2022}
}

@article{li2022visualizations,
 author = {Li, Jialu and Hasegawa-Johnson, Mark and McElwain, Nancy L},
 journal = {arXiv preprint arXiv:2203.15183},
 title = {Visualizations of Complex Sequences of Family-Infant Vocalizations Using Bag-of-Audio-Words Approach Based on Wav2vec 2.0 Features},
 url = {https://arxiv.org/pdf/2203.15183},
 year = {2022}
}

@inproceedings{qian2022contentvec,
 author = {Kaizhi Qian and Yang Zhang and Heting Gao and Junrui Ni and C.-I. Lai and David Cox
and Mark Hasegawa-Johnson and Shiyu Chang},
 booktitle = {Proc. International Conference on Machine Learning (ICML)},
 pages = {18003--18017},
 title = {Contentvec: An improved selfsupervised speech representation by disentangling speakers},
 url = {https://proceedings.mlr.press/v162/qian22b/qian22b.pdf},
 year = {2022}
}

@inproceedings{harvill22_interspeech,
 author = {John Harvill and Mark Hasegawa-Johnson and Chang D. Yoo},
 booktitle = {Proc. Interspeech 2022},
 doi = {10.21437/Interspeech.2022-204},
 pages = {2843--2847},
 title = {Frame-Level Stutter Detection},
 year = {2022}
}

@inproceedings{harvill2022estimation,
 author = {John Harvill and Yash Wani and Narendra Ahuja and Mark Hasegawa-Johnson and David Chestek and Mustafa Alam and David Beiser},
 booktitle = {44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society},
 keywords = {analysis},
 title = {Estimation of Respiratory Rate from Breathing Audio},
 url = {https://ieeexplore.ieee.org/document/9871897},
 year = {2022}
}

@article{gao2022domain,
 author = {Gao, Heting and Ni, Junrui and Zhang, Yang and Qian, Kaizhi and Chang, Shiyu and Hasegawa-Johnson, Mark},
 doi = {10.3389/frai.2022.806274},
 journal = {Frontiers in Artificial Intelligence},
 pages = {806274},
 publisher = {Frontiers Media SA},
 title = {Domain Generalization for Language-Independent Automatic Speech Recognition},
 volume = {5},
 year = {2022}
}

@inproceedings{yeh2022equivariance,
 author = {Raymond Yeh and Mark Hasegawa-Johnson and Alexander Schwing},
 booktitle = {AISTATS},
 keywords = {intelligence},
 title = {Equivariance Discovery by Learned Parameter-Sharing},
 url = {https://proceedings.mlr.press/v151/yeh22b/yeh22b.pdf},
 year = {2022}
}

@inproceedings{harvill2022syn2vec:,
 author = {John Harvill and Roxana Girju and Mark Hasegawa-Johnson},
 booktitle = {Proc. NAACL},
 doi = {10.18653/v1/2022.naacl-main.386},
 keywords = {intelligence},
 pages = {5259–5270},
 title = {Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity},
 url = {https://aclanthology.org/2022.naacl-main.386/},
 year = {2022}
}

@article{gao2022seamless,
 author = {Heting Gao and Xiaoxuan Wang and Sunghun Kang and Rusty Mina and Dias Issa and John Harvill and Leda Sarı and Mark Hasegawa-Johnson and Chang D. Yoo},
 doi = {10.1016/j.specom.2021.11.004},
 journal = {Speech Communication},
 keywords = {recognition},
 pages = {76-83},
 title = {Seamless Equal Accuracy Ratio for Inclusive CTC Speech Recognition},
 volume = {136},
 year = {2022}
}

@inproceedings{sari2022auxiliary,
 author = {Leda Sarı and Mark Hasegawa-Johnson and Samuel Thomas},
 booktitle = {IEEE Transactions on Audio, Speech, and Language},
 doi = {10.1109/TASLP.2020.3040626},
 keywords = {recognition},
 pages = {324-333},
 title = {Auxiliary Networks for Joint Speaker Adaptation and Speaker Change Detection},
 volume = {29},
 year = {2022}
}

@inproceedings{morshed22_interspeech,
 author = {Mahir Morshed and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2022},
 doi = {10.21437/Interspeech.2022-11202},
 pages = {2298--2302},
 title = {Cross-lingual articulatory feature information transfer for speech recognition using recurrent progressive neural networks},
 year = {2022}
}

@inproceedings{gao22e_interspeech,
 author = {Heting Gao and Junrui Ni and Kaizhi Qian and Yang Zhang and Shiyu Chang and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2022},
 doi = {10.21437/Interspeech.2022-11031},
 pages = {2738--2742},
 title = {WavPrompt: Towards Few-Shot Spoken Language Understanding with Frozen Language Models},
 year = {2022}
}

@inproceedings{ni22_interspeech,
 author = {Junrui Ni and Liming Wang and Heting Gao and Kaizhi Qian and Yang Zhang and Shiyu Chang and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2022},
 doi = {10.21437/Interspeech.2022-816},
 pages = {461--465},
 title = {Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition},
 year = {2022}
}

@inproceedings{chan2022speech,
 author = {Chak Ho Chan and Kaizhi Qian and Yang Zhang and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP43922.2022.9747763},
 pages = {6332-6336},
 title = {SpeechSplit2.0: Unsupervised Speech Disentanglement for Voice Conversion without Tuning Autoencoder Bottlenecks},
 url = {https://doi.org/10.1109/ICASSP43922.2022.9747763},
 year = {2022}
}

@mastersthesis{harvill2022dysarthric,
 author = {John Harvill},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Regularization for dysarthric speech recognition and telemedicine applications},
 url = {https://www.ideals.illinois.edu/items/124579},
 year = {2022}
}

@mastersthesis{guan2022study,
 author = {Haozhong Guan},
 school = {University of Illinois},
 title = {Study on speech emotion recognition based on deep learning},
 url = {https://www.ideals.illinois.edu/items/126694},
 year = {2022}
}

@mastersthesis{morshed2022cross,
 author = {Mahir Morshed},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Cross-lingual articulation information transfer with progressive networks for speech recognition},
 url = {https://www.ideals.illinois.edu/items/124791},
 year = {2022}
}

@mastersthesis{chan2022speech,
 author = {Chak Ho Chan},
 keywords = {analysis},
 school = {University of Illinois},
 title = {SpeechSplit2: Disentangling Speech Information Streams without Exhaustive Bottleneck Fine-tuning},
 url = {https://www.ideals.illinois.edu/items/118126},
 year = {2022}
}

@phdthesis{fan2021sparse,
 author = {Yuchen Fan},
 keywords = {vision},
 month = {November},
 school = {University of Illinois},
 title = {Sparse representation in deep vision models},
 url = {https://www.ideals.illinois.edu/items/123372},
 year = {2021}
}

@phdthesis{zhou2021towards,
 author = {Yuqian Zhou},
 keywords = {vision},
 month = {November},
 school = {University of Illinois},
 title = {Towards practical deep learning based image restoration model},
 url = {https://www.ideals.illinois.edu/items/123259},
 year = {2021}
}

@phdthesis{sari2021learning,
 author = {Leda Sarı},
 keywords = {recognition},
 month = {April},
 school = {University of Illinois},
 title = {Learning speech embeddings for speaker adaptation and speech understanding},
 url = {https://www.ideals.illinois.edu/items/118278},
 year = {2021}
}

@article{scharenborg2021international,
 author = {Odette Scharenborg and Mark Hasegawa-Johnson},
 doi = {10.1007/978-981-15-9323-9_36},
 editor = {Marchi, E., Siniscalchi, S.M., Cumani, S., Salerno, V.M., Li, H.},
 journal = {Lecture Notes in Computer Science},
 keywords = {recognition},
 month = {3},
 title = {Position Paper: Brain Signal-based Dialogue Systems},
 volume = {714},
 year = {2021}
}

@article{li2021analysis,
 author = {Jialu Li and Mark Hasegawa-Johnson and Nancy McElwain},
 doi = {10.1016/j.specom.2021.07.010},
 journal = {Speech Communication},
 keywords = {analysis},
 pages = {41-61},
 title = {Analysis of Acoustic and Voice Quality Features for the Classification of Infant and Mother Vocalizations},
 volume = {133},
 year = {2021}
}

@incollection{rosenberg2021oxford,
 author = {Andrew Rosenberg and Mark Hasegawa-Johnson},
 booktitle = {Oxford Handbook of Language Prosody},
 doi = {10.1093/oxfordhb/9780198832232.013.43},
 editor = {Carlos Gussenhoven and Aoju Chen},
 keywords = {analysis},
 pages = {646--656},
 publisher = {Oxford University Press},
 title = {Automatic Prosody Labeling and Assessment},
 year = {2021}
}

@inproceedings{zhu2021a,
 author = {Junzhe Zhu and Mark Hasegawa-Johnson and Nancy McElwain},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP39728.2021.9413538},
 keywords = {analysis},
 pages = {7178-7182},
 title = {A Comparison Study on Infant-Parent Voice Diarization},
 year = {2021}
}

@inproceedings{harvill2021classification,
 author = {John Harvill and Yash R. Wani and Mark Hasegawa-Johnson and Narendra Ahuja and David Beiser and David Chestek},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2021-799},
 keywords = {analysis},
 pages = {926--930},
 title = {Classification of COVID-19 from Cough Using Autoregressive Predictive Coding Pretraining and Spectral Data Augmentation},
 year = {2021}
}

@inproceedings{shi2021continuous,
 author = {Hui Shi and Yang Zhang and Hao Wu and Shiyu Chang and Kaizhi Qian and Mark Hasegawa-Johnson and Jishen Zhao},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP39728.2021.9414318},
 keywords = {intelligence},
 title = {Continuous CNN for Nonuniform Time Series},
 year = {2021}
}

@inproceedings{ramnath2021worldly,
 author = {Kiran Ramnath and Leda Sarı and Mark Hasegawa-Johnson and Chang Yoo},
 booktitle = {Proc. NAACL},
 doi = {10.18653/v1/2021.naacl-main.153},
 keywords = {intelligence},
 pages = {1908–1919},
 title = {Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering},
 year = {2021}
}

@inproceedings{wang2021interpretable,
 author = {Zhonghao Wang and Mo Yu and Kai Wang and Jinjun Xiaong and Wen-mei Hwu and Mark Hasegawa-Johnson and Humphrey Shi},
 booktitle = {ICCV},
 keywords = {intelligence},
 pages = {1878-1887},
 title = {Interpretable Visual Reasoning via Induced Symbolic Space},
 url = {https://openaccess.thecvf.com/content/ICCV2021/html/Wang_Interpretable_Visual_Reasoning_via_Induced_Symbolic_Space_ICCV_2021_paper.html},
 year = {2021}
}

@article{sari2021counterfactually,
 author = {Leda Sarı and Mark Hasegawa-Johnson and Chang D. Yoo},
 doi = {10.1109/TASLP.2021.3126949},
 journal = {IEEE Transactions on Audio, Speech, and Language},
 keywords = {recognition},
 pages = {3515-3525},
 title = {Counterfactually Fair Automatic Speech Recognition},
 volume = {29},
 year = {2021}
}

@inproceedings{gao2021zero-shot,
 author = {Heting Gao and Junrui Ni and Yang Zhang and Kaizhi Qian and Shiyu Chang and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2021-1843},
 keywords = {recognition},
 pages = {1304--1308},
 title = {Zero-shot Cross-Lingual Phonetic Recognition with External Language Embedding},
 year = {2021}
}

@inproceedings{feng2021how,
 author = {Siyuan Feng and Piotr Żelasko and Laureano Moro-Velázquez and Ali Abavisani and Mark Hasegawa-Johnson and Odette Scharenborg and Najim Dehak},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP39728.2021.9414478},
 keywords = {recognition},
 pages = {7238-7242},
 title = {How Phonotactics Affect Multilingual and Zero-shot ASR Performance},
 year = {2021}
}

@inproceedings{wang2021align,
 author = {Liming Wang and Xinsheng Wang and Mark Hasegawa-Johnson and Odette Scharenborg and Najim Dehak},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP39728.2021.9414418},
 keywords = {recognition},
 title = {Align or Attend? Toward More Efficient and Accurate Spoken Word Discovery Using Speech-to-Image Retrieval},
 year = {2021}
}

@inproceedings{harvill2021synthesis,
 author = {John Harvill and Dias Issa and Mark Hasegawa-Johnson and Changdong Yoo},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP39728.2021.9414869},
 keywords = {recognition},
 pages = {6428-6432},
 title = {Synthesis of New Words for Improved Dysarthric Speech Recognition on an Expanded Vocabulary},
 year = {2021}
}

@inproceedings{qian2021global,
 author = {Kaizhi Qian and Yang Zhang and Shiyu Chang and Chuang Gan and David D. Cox and Mark Hasegawa-Johnson and Jinjun Xiong},
 booktitle = {ICML},
 keywords = {synthesis},
 title = {Global Rhythm Style Transfer Without Text Transcriptions},
 url = {http://proceedings.mlr.press/v139/qian21b/qian21b.pdf},
 year = {2021}
}

@inproceedings{wang2021show,
 author = {Xinsheng Wang and Siyuan Feng and Jihua Zhu and Mark Hasegawa-Johnson and Odette Scharenborg},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP39728.2021.9414021},
 keywords = {synthesis},
 title = {Show and Speak: Directly Synthesize Spoken Description of Images},
 year = {2021}
}

@inproceedings{zhu2021multi-decoder,
 author = {Junzhe Zhu and Raymond Yeh and Mark Hasegawa-Johnson},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP39728.2021.9414205},
 keywords = {synthesis},
 pages = {3420-3424},
 title = {Multi-Decoder DPRNN: Source Separation for Variable Number of Speakers},
 year = {2021}
}

@mastersthesis{gao2021improving,
 author = {Heting Gao},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Improving multilingual speech recognition systems},
 url = {https://www.ideals.illinois.edu/items/123250},
 year = {2021}
}

@mastersthesis{ramnath2021fact,
 author = {Kiran Ramnath},
 keywords = {nlp},
 school = {University of Illinois},
 title = {Thumbnail for Fact-based visual question answering using knowledge graph embeddings
Fact-based visual question answering using knowledge graph embeddings},
 url = {https://www.ideals.illinois.edu/items/118412},
 year = {2021}
}

@mastersthesis{ni2021enforcing,
 author = {Ni, Junrui},
 school = {University of Illinois},
 title = {Enforcing constraints for multi-lingual and cross-lingual speech-to-text systems},
 url = {https://www.ideals.illinois.edu/items/123289/bitstreams/406101/data.pdf},
 year = {2021}
}

@phdthesis{qian2020deep,
 author = {Kaizhi Qian},
 keywords = {synthesis},
 month = {November},
 school = {University of Illinois},
 title = {Deep generative models for speech editing},
 url = {https://www.ideals.illinois.edu/items/117215},
 year = {2020}
}

@inproceedings{zhu2020identify,
 author = {Junzhe Zhu and Mark Hasegawa-Johnson and Leda Sari},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2020-2430},
 keywords = {analysis},
 pages = {3092--3096},
 title = {Identify Speakers in Cocktail Parties with End-to-End Attention},
 url = {https://arxiv.org/pdf/2005.11408.pdf},
 year = {2020}
}

@inproceedings{abavisani000086automatic,
 author = {Ali Abavisani and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2020-2121},
 keywords = {analysis},
 pages = {1161--1165},
 title = {Automatic Estimation of Intelligibility Measure for Consonants in Speech},
 url = {https://arxiv.org/abs/2005.06065},
 year = {2020}
}

@article{hasegawajohnson2020grapheme-to-phoneme,
 author = {Mark Hasegawa-Johnson and Leanne Rolston and Camille Goudeseune and Gina-Anne Levow and Katrin Kirchhoff},
 doi = {10.1007/978-3-030-59430-5_1},
 journal = {Lecture Notes in Computer Science},
 keywords = {recognition},
 pages = {3-19},
 title = {Grapheme-to-Phoneme Transduction for Cross-Language ASR},
 volume = {12379},
 year = {2020}
}

@inproceedings{li2020autosegmental,
 author = {Jialu Li and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2020-1834},
 keywords = {recognition},
 pages = {1027--1031},
 title = {Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous?},
 url = {http://arxiv.org/abs/2007.14351},
 year = {2020}
}

@inproceedings{zelasko2020that,
 author = {Piotr Żelasko and Laureano Moro-Velázquez and Mark Hasegawa-Johnson and Odette Scharenborg and Najim Dehak},
 booktitle = {Proc. Interspeech 2020},
 doi = {10.21437/Interspeech.2020-2513},
 keywords = {recognition},
 pages = {3705--3709},
 title = {That Sounds Familiar: An Analysis of Phonetic Representations Transfer Across Languages},
 year = {2020}
}

@inproceedings{van2020evaluating,
 author = {Justin van der Hout and Mark Hasegawa-Johnson and Odette Scharenborg},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2020-2870},
 keywords = {recognition},
 pages = {2317--2321},
 title = {Evaluating Automatically Generated Phoneme Captions for Images},
 url = {https://arxiv.org/abs/2007.15916},
 year = {2020}
}

@inproceedings{wang2020a,
 author = {Liming Wang and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2020-1148},
 keywords = {recognition},
 pages = {1456--1460},
 title = {A DNN-HMM-DNN Hybrid Model for Discovering Word-Like Units from Spoken Captions and Image Regions},
 year = {2020}
}

@article{wang2020multimodal,
 author = {Liming Wang and Mark Hasegawa-Johnson},
 doi = {10.1109/TASLP.2020.2996082},
 journal = {IEEE Transactions on Audio, Speech and Language},
 keywords = {recognition},
 pages = {1560-1573},
 title = {Multimodal word discovery and retrieval with spoken descriptions and visual concepts},
 volume = {28},
 year = {2020}
}

@inproceedings{hasegawajohnson2020multimodal,
 author = {Mark Hasegawa-Johnson},
 booktitle = {NeurIPS Workshop on Self-Supervised Learning for Speech and Audio},
 title = {Multimodal Distant Supervision},
 url = {https://slideslive.com/38938462/multimodal-distant-supervision},
 year = {2020}
}

@inproceedings{sari2020training,
 author = {Leda Sarı and Samuel Thomas and Mark Hasegawa-Johnson},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP40776.2020.9054664},
 keywords = {recognition},
 pages = {8109-8113},
 title = {Training Spoken Language Understanding Systems with Non-Parallel Speech and Text},
 year = {2020}
}

@inproceedings{sari2020deep,
 author = {Leda Sarı and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2020-1949},
 keywords = {recognition},
 pages = {1580--1584},
 title = {Deep F-Measure Maximization for End-to-End Speech Understanding},
 year = {2020}
}

@inproceedings{qian2020unsupervised,
 author = {Kaizhi Qian and Yang Zhang and Shiyu Chang and Mark Hasegawa-Johnson and David Cox},
 booktitle = {Proc. International Conference on Machine Learning (ICML)},
 demo = {https://auspicious3000.github.io/SpeechSplit-Demo/},
 keywords = {synthesis},
 pages = {7836--7846},
 title = {Unsupervised Speech Decomposition via Triple Information Bottleneck},
 url = {http://proceedings.mlr.press/v119/qian20a.html},
 volume = {119},
 year = {2020}
}

@inproceedings{qian2020f0-consistent,
 author = {Kaizhi Qian and Zeyu Jin and Mark Hasegawa-Johnson and Gautham Mysore},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP40776.2020.9054734},
 keywords = {synthesis},
 pages = {6284-6288},
 title = {F0-Consistent Many-to-Many Non-Parallel Voice Conversion via Conditional Autoencoder},
 year = {2020}
}

@inproceedings{sakakini2020automatic,
 author = {Tarek Sakakini and Jong Yoon Lee and Aditya Srinivasa and Renato Azevedo and Victor Sadauskas and Kuangxiao Gu and Suma Bhat and Dan Morrow and James Graumlich and Saqib Walayat and Mark Hasegawa-Johnson and Donald Wilpern and Ann Willemsen-Dunlap},
 booktitle = {LOUHI: 11th International Workshop on Health Text Mining and Information Analysis},
 keywords = {synthesis},
 title = {Automatic Text Simplification of Health Materials in Low-Resource Domains},
 url = {https://louhi2020.fbk.eu/},
 year = {2020}
}

@inproceedings{morrow2020closing,
 address = {Chicago, IL},
 author = {Daniel Morrow and Renato F.L. Azevedo and Leda Sari and Kuangxiao Gu and Tarek Sakakini and Mark Hasegawa-Johnson and Suma Bhat and James Graumlich and Thomas Huang and Andrew Hariharan and Yunxin Shao and Elizabeth Cox},
 booktitle = {Proceedings of the 2020 Human Factors and Ergonomics Society Annual Meeting},
 keywords = {synthesis},
 title = {Closing the Loop in Computer Agent/Patient Communication},
 year = {2020}
}

@incollection{kim2020communication,
 address = {Boston/Berlin},
 author = {Heejin Kim and Mark Hasegawa-Johnson},
 booktitle = {Acoustic Analysis of Pathologies: From Infancy to Young Adulthood},
 doi = {10.1515/9781501513138-005},
 editor = {Amy Neustein and Hemant Patil},
 pages = {181--197},
 publisher = {Walter De Gruyter, Inc.},
 title = {Communication Improves When Human or Computer Listeners Adapt to Dysarthria},
 year = {2020}
}

@mastersthesis{zhu2020multi,
 author = {Junzhe Zhu},
 keywords = {enhancement},
 school = {University of Illinois},
 title = {Multi-decoder DPRNN high accuracy source counting and separation},
 url = {https://www.ideals.illinois.edu/items/116889},
 year = {2020}
}

@mastersthesis{wu2020semi,
 author = {Ningkai Wu},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Semi-supervised cycle-consistency training for end-to-end ASR using unpaired speech},
 url = {https://www.ideals.illinois.edu/items/115809},
 year = {2020}
}

@mastersthesis{wang2020translation,
 author = {Liming Wang},
 keywords = {analysis},
 school = {University of Illinois},
 title = {A translation framework for discovering word-like units from visual scenes and spoken descriptions},
 url = {https://www.ideals.illinois.edu/items/115664},
 year = {2020}
}

@article{ni2019the,
 author = {Junrui Ni and Mark Hasegawa-Johnson and Odette Scharenborg},
 doi = {10.1007/978-3-030-31372-2_1},
 journal = {Lecture Notes in Artificial Intelligence},
 keywords = {analysis},
 month = {October},
 pages = {3-18},
 title = {The Time-Course of Phoneme Category Adaptation in Deep Neural Networks},
 url = {https://www.researchgate.net/profile/Odette_Scharenborg/publication/336096664_The_Time-Course_of_Phoneme_Category_Adaptation_in_Deep_Neural_Networks/links/5db0627e4585155e27f81326/The-Time-Course-of-Phoneme-Category-Adaptation-in-Deep-Neural-Networks.pdf},
 volume = {11816},
 year = {2019}
}

@phdthesis{chen2019modeling,
 author = {Wenda Chen},
 keywords = {recognition},
 month = {July},
 school = {University of Illinois},
 title = {Modeling phones, keywords, topics and intents in spoken languages},
 url = {https://www.ideals.illinois.edu/items/112912},
 year = {2019}
}

@phdthesis{yang2019dealing,
 author = {Xuesong Yang},
 keywords = {recognition},
 month = {May},
 school = {University of Illinois},
 title = {Dealing with linguistic mismatches for automatic speech recognition},
 url = {https://www.ideals.illinois.edu/items/112306},
 year = {2019}
}

@inproceedings{sari2019pre-training,
 author = {Leda Sari and Samuel Thomas and Mark Hasegawa-Johnson and Michael Picheny},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2019.8683612},
 keywords = {analysis},
 pages = {3093:1-5},
 title = {Pre-Training of Speaker Embeddings for Low-Latency Speaker Change Detection in Broadcast News},
 year = {2019}
}

@inproceedings{scharenborg2019the,
 author = {Odette Scharenborg and Jiska Koemans and Cybelle Smith and Mark A. Hasegawa-Johnson and Kara D. Federmeier},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2019-2328},
 keywords = {analysis},
 pages = {1223--1227},
 title = {The Neural Correlates Underlying Lexically-Guided Perceptual Learning},
 year = {2019}
}

@inproceedings{pietrowicz2019dimensional,
 author = {Mary Pietrowicz and Carla Agurto and Jonah Casebeer and Mark Hasegawa-Johnson and Karrie Karahalios and Guillermo Cecchi},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2019.8683566},
 keywords = {analysis},
 pages = {6600-6604},
 title = {Dimensional Analysis of Laughter in Female Conversational Speech},
 url = {https://ieeexplore.ieee.org/abstract/document/8683566},
 year = {2019}
}

@inproceedings{sar19_interspeech,
 author = {Leda Sarı and Samuel Thomas and Mark A. Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2019},
 doi = {10.21437/Interspeech.2019-1788},
 pages = {769--773},
 title = {Learning Speaker Aware Offsets for Speaker Adaptation of Neural Networks},
 year = {2019}
}

@inproceedings{he2150when,
 author = {Di He and Xuesong Yang and Boon Pang Lim and Yi Liang and Mark Hasegawa-Johnson and Deming Chen},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2019.8683607},
 keywords = {recognition},
 pages = {5996-6000},
 title = {When CTC Training Meets Acoustic Landmarks},
 year = {2019}
}

@inproceedings{wang2019multimodal,
 author = {Liming Wang and Mark A. Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2019-1487},
 keywords = {recognition},
 pages = {2683--2687},
 title = {Multimodal Word Discovery and Retrieval with Phone Sequence and Image Concepts},
 year = {2019}
}

@inproceedings{hasegawajohnson2019position,
 author = {Mark Hasegawa-Johnson and Najim Dehak and Odette Scharenborg},
 booktitle = {International Workshop on Spoken Dialog Systems},
 keywords = {recognition},
 title = {Position Paper: Indirect Supervision for Dialog Systems in Unwritten Languages},
 url = {https://research.tudelft.nl/files/83277474/IWSDS_2019_Mark.pdf},
 year = {2019}
}

@inproceedings{morovelazquez2019study,
 author = {Laureano Moro-Velazquez and JaeJin Cho and Shinji Watanabe and Mark A. Hasegawa-Johnson and Odette Scharenborg and Heejin Kim and Najim Dehak},
 booktitle = {Proc. Interspeech 2019},
 doi = {10.21437/Interspeech.2019-2993},
 keywords = {recognition},
 pages = {3875--3879},
 title = {Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinson’s Disease},
 year = {2019}
}

@article{qian2019autovc:,
 author = {Kaizhi Qian and Yang Zhang and Shiyu Chang and Xuesong Yang and Mark Hasegawa-Johnson},
 demo = {https://auspicious3000.github.io/autovc-demo/},
 journal = {Proceedings of Machine Learning Research},
 keywords = {synthesis},
 pages = {5210-5219},
 title = {AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss},
 url = {http://proceedings.mlr.press/v97/qian19c/qian19c.pdf},
 volume = {97},
 year = {2019}
}

@article{morrow2019contextualizing,
 author = {Daniel Morrow and Renato Azevedo and Leitão Ferreira and Rocio Garcia-Retamero and Mark Hasegawa-Johnson and Thomas Huang and William Schuh and Kuangxiao Gu and Yang Zhang},
 doi = {10.1037/xap0000203},
 journal = {Journal of Experimental Psychology: Applied},
 keywords = {synthesis},
 number = {1},
 pages = {41-61},
 title = {Contextualizing numeric clinical test results for gist comprehension: Implications for EHR patient portals},
 volume = {25},
 year = {2019}
}

@inproceedings{azevedo2019the,
 author = {Renato F.L. Azevedo and Dan Morrow and Kuangxiao Gu and Thomas Huang and Mark Hasegawa-Johnson and P. Soni and S. Tang and Tarek Sakakini and Suma Bhat and Ann Willemsen-Dunlap and James Graumlich},
 booktitle = {Proceedings of the 2019 Human Factors and Ergonomics Society Health Care Symposium},
 keywords = {synthesis},
 title = {The Influence of Computer Agent Characteristics on User Preferences in Health Contexts},
 year = {2019}
}

@mastersthesis{xu2019acoustic,
 author = {Yijia Xu},
 keywords = {analysis},
 school = {University of Illinois},
 title = {Acoustic Event, Spoken Keyword and Emotional Outburst Detection},
 url = {https://www.ideals.illinois.edu/items/112277},
 year = {2019}
}

@article{hai2018multitask,
 author = {Van Hai Do and Nancy F. Chen and Boon Pang Lim and Mark Hasegawa-Johnson},
 doi = {10.1109/TASLP.2017.2782360},
 journal = {IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)},
 keywords = {recognition},
 month = {March},
 number = {3},
 pages = {501-514},
 title = {Multitask Learning for Phone Recognition of Underresourced Languages Using Mismatched Transcription},
 url = {https://dl.acm.org/citation.cfm?id=3180760},
 volume = {26},
 year = {2018}
}

@inproceedings{xu2018infant,
 author = {Yijia Xu and Mark Hasegawa-Johnson and Nancy L. McElwain},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2018-2429},
 keywords = {analysis},
 pages = {242--246},
 title = {Infant emotional outbursts detection in infant-parent spoken interactions},
 year = {2018}
}

@unpublished{hasegawajohnson2018unwritten,
 author = {Mark Hasegawa-Johnson},
 keywords = {analysis},
 note = {Plenary talk delivered at the International Symposium on Chinese Spoken Language Processing},
 title = {Unwritten Languages as a Test Case for the Theory of Phonetic Universals},
 year = {2018}
}

@inproceedings{yeh2018image,
 author = {Raymond A. Yeh and Teck Yian Lim and Chen Chen and Alexander G. Schwing and Mark Hasegawa-Johnson and Minh N. Do},
 booktitle = {Proc. IEEE ICASSP},
 doi = {10.1109/ICASSP.2018.8462317},
 keywords = {intelligence},
 pages = {6772-6772},
 title = {Image Restoration with Deep Generative Models},
 url = {https://ieeexplore.ieee.org/abstract/document/8462317},
 year = {2018}
}

@inproceedings{li2018a,
 author = {Jialu Li and Mark Hasegawa-Johnson},
 booktitle = {NeurIPS Workshop on Interpretability and Robustness in Audio, Speech, and Language},
 keywords = {recognition},
 title = {A Comparable Phone Set for the TIMIT Dataset Discovered in Clustering of Listen, Attend and Spell},
 year = {2018}
}

@inproceedings{scharenborg2018visualizing,
 author = {Odette Scharenborg and Sebastian Tiesmeyer and Mark Hasegawa-Johnson and Najim Dehak},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2018-1707},
 keywords = {recognition},
 pages = {1482--1486},
 title = {Visualizing Phoneme Category Adaptation in Deep Neural Networks},
 year = {2018}
}

@inproceedings{sari2018mlslp,
 author = {Leda Sari and Mark Hasegawa-Johnson},
 booktitle = {MLSLP (ISCA Workshop on Machine Learning for Speech and Language Processing)},
 keywords = {recognition},
 title = {Speaker Adaptation with an Auxiliary Network},
 year = {2018}
}

@inproceedings{he2018improved,
 author = {Di He and Boon Pang Lim and Xuesong Yang and Mark Hasegawa-Johnson and Deming Chen},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2018-1124},
 keywords = {recognition},
 pages = {2618--2622},
 title = {Improved ASR for under-resourced languages through Multi-task Learning with Acoustic Landmarks},
 year = {2018}
}

@phdthesis{das2018speech,
 author = {Amit Das},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Speech Recognition with Probabilistic Transcriptions and End-to-End Systems Using Deep Learning},
 url = {https://www.ideals.illinois.edu/items/109828},
 year = {2018}
}

@inproceedings{das2018improving,
 author = {Amit Das and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2018-1450},
 keywords = {recognition},
 pages = {2434--2438},
 title = {Improving DNNs Trained With Non-Native Transcriptions Using Knowledge Distillation and Target Interpolation},
 year = {2018}
}

@inproceedings{ondel2018bayesian,
 author = {Lucas Ondel and Pierre Godard and Laurent Besacier and Elin Larsen and Mark Hasegawa-Johnson and Odette Scharenborg and Emmanuel Dupoux and Lukas Burget and François Yvon and Sanjeev Khudanpur},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2018.8461545},
 keywords = {recognition},
 pages = {5939-5943},
 title = {Bayesian Models for Unit Discovery on a Very Low Resource Language},
 year = {2018}
}

@inproceedings{chen2018recognizing,
 author = {Wenda Chen and Mark Hasegawa-Johnson and Nancy Chen},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2018.8462481},
 keywords = {recognition},
 pages = {5979-5983},
 title = {Recognizing Zero-resourced Languages based on Mismatched Machine Transcriptions},
 url = {https://ieeexplore.ieee.org/abstract/document/8462481},
 year = {2018}
}

@inproceedings{yang2018joint,
 author = {Xuesong Yang and Kartik Audhkhasi and Andrew Rosenberg and Samuel Thomas and Bhuvana Ramabhadran and Mark Hasegawa-Johnson},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2018.8462557},
 keywords = {recognition},
 pages = {5989-5993},
 title = {Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition},
 url = {https://ieeexplore.ieee.org/abstract/document/8462557},
 year = {2018}
}

@article{he2018acoustic,
 author = {Di He and Boon Pang Lim and Xuesong Yang and Mark Hasegawa-Johnson and Deming Chen},
 doi = {10.1121/1.5039837},
 journal = {Journal of the Acoustical Society of America},
 keywords = {recognition},
 number = {6},
 pages = {3207-3219},
 title = {Acoustic landmarks contain more information about the phone string than other frames for automatic speech recognition with deep neural network acoustic model},
 url = {https://asa.scitation.org/doi/full/10.1121/1.5039837},
 volume = {143},
 year = {2018}
}

@inproceedings{sari2018interspeech,
 author = {Leda Sari and Mark Hasegawa-Johnson and S. Kumaran and Georg Stemmer and N. Nair Krishnakumar},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2018-2359},
 keywords = {recognition},
 pages = {3524--3528},
 title = {Speaker Adaptive Audio-Visual Fusion for the Open-Vocabulary Section of AVICAR},
 year = {2018}
}

@inproceedings{scharenborg2018building,
 author = {Odette Scharenborg and Patrick Ebel and Francesco Ciannella and Mark Hasegawa-Johnson and Najim Dehak},
 booktitle = {Proc. SLTU (Speech and Language Technology for Under-resourced languages)},
 doi = {10.21437/SLTU.2018-35},
 keywords = {recognition},
 pages = {167--171},
 title = {Building an ASR System for Mboshi Using a Cross-language Definition of Acoustic Units Approach},
 year = {2018}
}

@inproceedings{scharenborg2018linguistic,
 author = {Odette Scharenborg and Laurent Besacier and Alan Black and Mark Hasegawa-Johnson and Florian Metze and Graham Neubig and Sebastian Stüker and Pierre Godard and Markus Müller and Lucas Ondel and Shruti Palaskar and Philip Arthur and Francesco Ciannella and Mingxing Du and Elin Larsen and Danny Merkx and Rachid Riad and Liming Wang and Emmanuel Dupoux},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2018.8461761},
 keywords = {recognition},
 title = {Linguistic Unit Discovery from Multi-Modal Inputs in Unwritten Languages: Summary of the Speaking Rosetta JSALT 2017 Workshop},
 year = {2018}
}

@inproceedings{chen2018topic,
 author = {Wenda Chen and Mark Hasegawa-Jonson and Nancy F.Y. Chen},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2018-1283},
 keywords = {recognition},
 pages = {2047--2051},
 title = {Topic and Keyword Identification for Low-resourced Speech Using Cross-Language Transfer Learning},
 year = {2018}
}

@inproceedings{hasegawajohnson2018image2speech:,
 author = {Mark Hasegawa-Johnson and Alan Black and Lucas Ondel and Odette Scharenborg and Francesco Ciannella},
 booktitle = {Journal of the International Science and General Applications (ISGA)},
 keywords = {synthesis},
 number = {1},
 title = {Image2speech: Automatically generating audio descriptions of images},
 url = {https://www.researchgate.net/profile/Kamel-Smaili-2/publication/354700462_INTERNATIONAL_CONFERENCE_ON_NATURAL_LANGUAGE_SIGNAL_AND_SPEECH_PROCESSING_Casablanca_2017_Morocco_Sponsor_ICNLSSP_International_Conference_on_Natural_Language_Signal_and_Speech_Processing/links/6148a03ea595d06017dd226b/INTERNATIONAL-CONFERENCE-ON-NATURAL-LANGUAGE-SIGNAL-AND-SPEECH-PROCESSING-Casablanca-2017-Morocco-Sponsor-ICNLSSP-International-Conference-on-Natural-Language-Signal-and-Speech-Processing.pdf#page=66},
 volume = {1},
 year = {2018}
}

@inproceedings{yian2018time-frequency,
 author = {Teck Yian Lim and Raymond Yeh and Yijia Xu and Minh Do and Mark Hasegawa-Johnson},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2018.8462049},
 keywords = {synthesis},
 title = {Time-Frequency Networks for Audio Super-Resolution},
 year = {2018}
}

@inproceedings{qian2018deep,
 author = {Kaizhi Qian and Yang Zhang and Shiyu Chang and Xuesong Yang and Dinei Florencio and Mark Hasegawa-Johnson},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2018.8462430},
 keywords = {synthesis},
 pages = {5389-5393},
 title = {Deep Learning Based Speech Beamforming},
 year = {2018}
}

@inproceedings{azevedo2018using,
 author = {Renato F. L. Azevedo and Dan Morrow and James Graumlich Ann Willemsen-Dunlap Mark Hasegawa-Johnson Thomas S. Huang and Kuangxiao Gu and Suma Bhat and Tarek Sakakini and Victor Sadauskas and Donald J. Halpin},
 booktitle = {AMIA Annu Symp Proc.},
 keywords = {synthesis},
 pages = {185–194},
 pmid = {30815056},
 title = {Using conversational agents to explain medication instructions to older adults},
 url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6371340/},
 year = {2018}
}

@inproceedings{azevedo2018computer,
 author = {Renato Azevedo and Daniel G. Morrow and Kuangxiao Gu and  Thomas Huang and Mark Allan Hasegawa-Johnson and James Graumlich and Victor Sadauskas and Tarek J. Sakakini and Suma Pallathadka Bhat and Ann M. Willemsen-Dunlap and Donald J. Halpin},
 booktitle = {APA Annual Meeting},
 keywords = {synthesis},
 title = {Computer Agents and Patient Memory for Medication Information},
 year = {2018}
}

@unpublished{wang2018multimodal,
 author = {Liming Wang},
 keywords = {analysis},
 note = {Unpublished B.S. thesis},
 school = {University of Illinois},
 title = {Multimodal semantic learning with context-correlated speeches and images},
 url = {https://www.ideals.illinois.edu/items/106072},
 year = {2018}
}

@mastersthesis{qian2018speech,
 author = {Kaizhi Qian},
 keywords = {enhancement},
 school = {University of Illinois},
 title = {Speech enhancement using deep dilated CNN},
 url = {https://www.ideals.illinois.edu/items/107741},
 year = {2018}
}

@inproceedings{kong2017landmark-based,
 address = {Boston},
 author = {Xiang Kong and Xuesong Yang and Jeung-Yoon Choi and Mark Hasegawa-Johnson and Stefanie Shattuck-Hufnagel},
 booktitle = {Acoustics 17},
 doi = {10.1121/1.4987203},
 keywords = {analysis},
 month = {June},
 title = {Landmark-based consonant voicing detection on multilingual corpora},
 url = {https://arxiv.org/pdf/1611.03533.pdf},
 year = {2017}
}

@inproceedings{he2017selecting,
 address = {Boston},
 author = {Di He and Boon Pang Lim and Xuesong Yang and Mark Hasegawa-Johnson and Deming Chen},
 booktitle = {Acoustics 17},
 doi = {10.1121/1.4987204},
 keywords = {analysis},
 month = {June},
 title = {Selecting frames for automatic speech recognition based on acoustic landmarks},
 url = {https://asa.scitation.org/doi/abs/10.1121/1.4987204},
 year = {2017}
}

@inproceedings{kong2017landmark,
 address = {Boston},
 author = {Xiang Kong and Xuesong Yang and Jeung-Yoon Choi and Mark Hasegawa-Johnson and Stefanie Shattuck-Hufnagel},
 booktitle = {Acoustics 17},
 doi = {10.1121/1.4987203},
 keywords = {recognition},
 month = {June},
 title = {Landmark-based consonant voicing detection on multilingual corpora},
 year = {2017}
}

@article{morrow2018a,
 author = {Daniel Morrow and Mark Hasegawa-Johnson and Thomas Huang and William Schuh and Renato Azevedo and Kuangxiao Gu and Yang Zhang and Bidisha Roy and Rocio Garcia-Retamero},
 doi = {10.1016/j.jbi.2017.03.015},
 journal = {Journal of Biomedical Informatics},
 keywords = {synthesis},
 month = {5},
 pages = {63-74},
 title = {A Multidisciplinary Approach to Designing and Evaluating Electronic Medical Record Portal Messages that Support Patient Self-Care},
 volume = {69},
 year = {2017}
}

@inproceedings{he2017using,
 author = {Di He and Zuofu Cheng and Mark Hasegawa-Johnson and Deming Chen},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2017-593},
 keywords = {analysis},
 pages = {1914--1918},
 title = {Using Approximated Auditory Roughness as a Pre-filtering Feature for Human Screaming and Affective Speech AED},
 year = {2017}
}

@phdthesis{pietrowicz2017exposing,
 author = {Mary Pietrowicz},
 keywords = {analysis},
 school = {University of Illinois},
 title = {Exposing the Hidden Vocal Channel: Analysis of Vocal Expression},
 url = {https://www.ideals.illinois.edu/items/105321},
 year = {2017}
}

@inproceedings{pietrowicz2017discovering,
 author = {Mary Pietrowicz and Mark Hasegawa-Johnson and Karrie Karahaliqos},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2017.7953247},
 keywords = {analysis},
 pages = {2901:1-4},
 title = {Discovering Dimensions of Perqceived Vocal Expression in Semi-Structured, Unscripted Oral History Accoqunts},
 year = {2017}
}

@phdthesis{serwy2017hilbert,
 author = {Roger Serwy},
 keywords = {analysis},
 school = {University of Illinois},
 title = {Hilbert Phase Methods for Glottal Activity Detection},
 url = {https://www.ideals.illinois.edu/items/102357},
 year = {2017}
}

@inproceedings{hasegawajohnson000187mismatched,
 author = {Mark Hasegawa-Johnson and Preethi Jyothi and Wenda Chen and Van Hai Do},
 booktitle = {Proceedings of Asilomar},
 doi = {10.1109/ACSSC.2017.8335558},
 grant = {DARPA LORELEI},
 keywords = {analysis},
 title = {Mismatched Crowdsourcing: Mining Latent Skills to Acquire Speech Transcriptions},
 year = {2017}
}

@inproceedings{chang2017dilated,
 author = {Shiyu Chang and Yang Zhang and Wei Han and Mo Yu andXiaoxiao Guo and Wei Tan and Xiaodong Cui and Michael Witbrock and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {NIPS},
 keywords = {intelligence},
 title = {Dilated Recurrent Neural Networks},
 url = {https://papers.nips.cc/paper/6613-dilated-recurrent-neural-networks.pdf},
 year = {2017}
}

@inproceedings{chang2017streaming,
 author = {Shiyu Chang and Yang Zhang and Jiling Tang and Dawei Yin and Yi Chang and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {WWW 2017},
 doi = {10.1145/3038912.3052627},
 keywords = {intelligence},
 pages = {381--389},
 title = {Streaming Recommender Systems},
 year = {2017}
}

@inproceedings{yeh2017semantic,
 author = {Raymond Yeh and Chen Chen and Teck Yian Lim and Alexander G. Schwing and Mark Hasegawa-Johnson and Minh N. Do},
 booktitle = {CVPR},
 keywords = {intelligence},
 pages = {5485-5493},
 title = {Semantic Image Inpainting with Deep Generative Networks},
 url = {https://openaccess.thecvf.com/content_cvpr_2017/html/Yeh_Semantic_Image_Inpainting_CVPR_2017_paper},
 year = {2017}
}

@inproceedings{do17_interspeech,
 author = {Van Hai Do and Nancy F. Chen and Boon Pang Lim and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2017},
 doi = {10.21437/Interspeech.2017-788},
 pages = {734--738},
 title = {Multi-Task Learning Using Mismatched Transcription for Under-Resourced Speech Recognition},
 year = {2017}
}

@inproceedings{scharenborg2017building,
 address = {Casablanca, Morocco},
 author = {Odette Scharenborg and Francesco Ciannella and Shruti Palaskar and Alan Black and Florian Metze and Lucas Ondel and Mark Hasegawa-Johnson},
 booktitle = {Proc. Internat. Conference on Natural Language, Signal and Speech Processing (ICNLSSP)},
 keywords = {recognition},
 title = {Building an ASR System for a Low-Resource Language Through the Adaptation of a High-Resource Language ASR System: Preliminary Results},
 url = {https://www.researchgate.net/profile/Kamel-Smaili-2/publication/354824671_Proceedings_of_the_International_Conference_on_Natural_Language_Processing_Signal_and_Speech_Processing/links/63503ccc12cbac6a3eda8cac/Proceedings-of-the-International-Conference-on-Natural-Language-Processing-Signal-and-Speech-Processing.pdf#page=28},
 year = {2017}
}

@inproceedings{chen2017mismatched,
 author = {Wenda Chen and Mark Hasegawa-Johnson and Nancy F. Chen and Boon Pang Lim},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2017-1567},
 keywords = {recognition},
 pages = {2789--2793},
 title = {Mismatched Crowdsourcing from Multiple Annotator Languages For Recognizing Zero-resourced Languages: A Nullspace Clustering Approach},
 year = {2017}
}

@inproceedings{papadopoulos2017team,
 author = {Pavlos Papadopoulos and Ruchir Travadi and Colin Vaz and Nikolaos Malandrakis and Ulf Hermjakob and Nima Pourdamghani and Michael Pust and Boliang Zhang and Xiaoman Pan and Di Lu and Ying Lin and Ondrej Glembek and Murali Karthick B and Martin Karafiat and Lukas Burget and Mark Hasegawa-Johnson and Heng Ji and Jonathan May and Kevin Knight and Shrikanth Narayanan},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2017-180},
 keywords = {recognition},
 pages = {2053--2057},
 title = {Team ELISA System for DARPA LORELEI Speech Evaluation 2016},
 year = {2017}
}

@inproceedings{das2017deep,
 author = {Amit Das and Mark Hasegawa-Johnson and Karel Vesely},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2017-582},
 keywords = {recognition},
 pages = {2073--2077},
 title = {Deep Autoencoder Based Multi-task Learning Using Probabilistic Transcription},
 year = {2017}
}

@phdthesis{zhang2017generative,
 author = {Yang Zhang},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Application of Generative Models in Speech Processing Tasks},
 url = {https://www.ideals.illinois.edu/items/103415},
 year = {2017}
}

@inproceedings{hasegawajohnson2017image2speech:,
 address = {Casablanca, Morocco},
 author = {Mark Hasegawa-Johnson and Alan Black and Lucas Ondel and Odette Scharenborg and Francesco Ciannella},
 booktitle = {Proc. Internat. Conference on Natural Language, Signal and Speech Processing (ICNLSSP)},
 keywords = {recognition},
 title = {Image2speech: Automatically generating audio descriptions of images},
 url = {https://www.researchgate.net/profile/Kamel-Smaili-2/publication/354700462_INTERNATIONAL_CONFERENCE_ON_NATURAL_LANGUAGE_SIGNAL_AND_SPEECH_PROCESSING_Casablanca_2017_Morocco_Sponsor_ICNLSSP_International_Conference_on_Natural_Language_Signal_and_Speech_Processing/links/6148a03ea595d06017dd226b/INTERNATIONAL-CONFERENCE-ON-NATURAL-LANGUAGE-SIGNAL-AND-SPEECH-PROCESSING-Casablanca-2017-Morocco-Sponsor-ICNLSSP-International-Conference-on-Natural-Language-Signal-and-Speech-Processing.pdf#page=66},
 year = {2017}
}

@article{hasegawajohnson2017asr,
 author = {Mark Hasegawa-Johnson and Preethi Jyothi and Daniel McCloy and Majid Mirbagheri and Giovanni di Liberto and Amit Das and Bradley Ekin and Chunxi Liu and Vimal Manohar and Hao Tang and Edmund C. Lalor and Nancy Chen and Paul Hager and Tyler Kekona and Rose Sloan and Adrian KC Lee},
 doi = {10.1109/TASLP.2016.2621659},
 issn = {2329-9290},
 journal = {IEEE/ACM Trans. Audio, Speech and Language},
 keywords = {recognition},
 number = {1},
 pages = {46-59},
 title = {ASR for Under-Resourced Languages from Probabilistic Transcription},
 volume = {25},
 year = {2017}
}

@inproceedings{zhang17j_interspeech,
 author = {Yang Zhang and Dinei Florêncio and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2017},
 doi = {10.21437/Interspeech.2017-1659},
 pages = {2675--2679},
 title = {Glottal Model Based Speech Beamforming for ad-hoc Microphone Arrays},
 year = {2017}
}

@inproceedings{qian2017speech,
 author = {Kaizhi Qian and Yang Zhang and Shiyu Chang and Xuesong Yang and Dinei Florencio and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2017-1672},
 keywords = {synthesis},
 pages = {2013--2017},
 title = {Speech Enhancement Using Bayesian Wavenet},
 year = {2017}
}

@unpublished{dupoux2017speaking,
 author = {Emmanuel Dupoux and Odette Scharenborg and Graham Neubig and Laurent Besacier and Mark Hasegawa-Johnson and Alan Black and Florian Metze and Sebastian Stüker},
 note = {Final report of the WS17 Frederick Jelinek Memorial Summer Workshop team},
 title = {The Speaking Rosetta Stone - Discovering Grounded Linguistic Units for Languages without Orthography},
 url = {https://www.lti.cs.cmu.edu/2017-jelinek-workshop},
 year = {2017}
}

@mastersthesis{zhu2017thumbnail,
 author = {Tianyilin Zhu},
 keywords = {multimodal},
 school = {University of Illinois},
 title = {Thumbnail for Lipreading with convolutional and recurrent neural network models
Lipreading with convolutional and recurrent neural network models},
 url = {https://www.ideals.illinois.edu/items/102816},
 year = {2017}
}

@inproceedings{hai2016speech,
 address = {Tainan, Taiwan},
 author = {Van Hai Do and Nancy F. Chen and Boon Pang Lim and Mark Hasegawa-Johnson},
 booktitle = {International Conference on Asian Language Processing IALP},
 doi = {10.1109/IALP.2016.7875947},
 keywords = {recognition},
 month = {11},
 title = {Speech recognition of under-resourced languages using mismatched transcriptions},
 year = {2016}
}

@inproceedings{hai2016a,
 address = {Hanoi, Vietnam},
 author = {Van Hai Do and Nancy F. Chen and Boon Pang Lim and Mark Hasegawa-Johnson},
 booktitle = {12th IEEE-RIVF International Conference on Computing and Communication Technologies},
 doi = {10.1109/RIVF.2016.7800280},
 keywords = {recognition},
 month = {11},
 pages = {120-124},
 title = {A many-to-one phone mapping approach for cross-lingual speech recognition},
 year = {2016}
}

@inproceedings{morrow2016multimedia,
 author = {Daniel Morrow and Mark Hasegawa-Johnson and Thomas Huang and William Schuh and Rocio Garcia-Retamero and Renato Azevedo and Kuangxiao Gu and Yang Zhang and Bidisha Roy},
 booktitle = {28th APS Annual Convention (Association for Psychological Science},
 grant = {AHRQ R21HS022948},
 keywords = {synthesis},
 month = {May},
 title = {Multimedia formats can improve older adult comprehension of clinical test results: Implications for Designing Patient Portals},
 year = {2016}
}

@unpublished{hasegawajohnson2016speech,
 author = {Mark Hasegawa-Johnson},
 keywords = {analysis},
 month = {January},
 note = {Lecture given at the Winter School on Speech and Audio Processing, Chennai, India},
 title = {Speech Production, Speech Perception, and Phonology},
 year = {2016}
}

@unpublished{hasegawajohnson2016prosody,
 author = {Mark Hasegawa-Johnson},
 keywords = {analysis},
 month = {January},
 note = {Lecture given at the Winter School on Speech and Audio Processing, Chennai, India},
 title = {Prosody},
 year = {2016}
}

@unpublished{hasegawajohnson2016multivariate,
 author = {Mark Hasegawa-Johnson},
 keywords = {analysis},
 month = {January},
 note = {Lecture given at the Winter School on Speech and Audio Processing, Chennai, India},
 title = {Multivariate-State Models for Speech Recognition},
 year = {2016}
}

@unpublished{hasegawajohnson2016limited,
 author = {Mark Hasegawa-Johnson},
 keywords = {analysis},
 month = {January},
 note = {Lecture given at the Winter School on Speech and Audio Processing, Chennai, India},
 title = {Limited Data Settings},
 year = {2016}
}

@inproceedings{yang2016landmarkbased,
 author = {Xuesong Yang and Xiang Kong and Mark Hasegawa-Johnson and Yanlu Xie},
 booktitle = {Speech Prosody},
 doi = {10.21437/SpeechProsody.2016-51},
 keywords = {analysis},
 pages = {247--251},
 title = {Landmark-based Pronunciation Error Identification on L2 Mandarin Chinese},
 year = {2016}
}

@article{livescu2016speech,
 author = {Karen Livescu and Frank Rudzicz and Eric Fosler-Lussier and Mark Hasegawa-Johnson and Jeff Bilmes},
 doi = {10.1016/j.csl.2015.11.002},
 journal = {Computer Speech and Language},
 keywords = {analysis},
 pages = {165-172},
 title = {Speech Production in Speech Technologies: Introduction to the CSL Special Issue},
 volume = {36},
 year = {2016}
}

@article{chen2016mismatched,
 author = {Wenda Chen and Mark Hasegawa-Johnson and Nancy F. Chen},
 doi = {10.1016/j.procs.2016.04.025},
 journal = {Procedia Computer Science},
 keywords = {analysis},
 pages = {23--29},
 title = {Mismatched Crowdsourcing based Language Perception for Under-resourced Languages},
 volume = {81},
 year = {2016}
}

@inproceedings{xie2016landmark,
 author = {Yanlu Xie and Mark Hasegawa-Johnson and Leyuan Qu and Jinsong Zhang},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2016.7472703},
 keywords = {analysis},
 title = {Landmark of Mandarin Nasal Codas and its Application in Pronunciation Error Detection},
 year = {2016}
}

@inproceedings{zhang2016analysis,
 author = {Yang Zhang and Gautham Mysore and Florian Berthouzoz and Mark Hasegawa-Johnson},
 booktitle = {Speech Prosody},
 doi = {10.21437/SpeechProsody.2016-17},
 keywords = {analysis},
 pages = {79--83},
 title = {Analysis of Prosody Increment Induced by Pitch Accents for Automatic Emphasis Correction},
 year = {2016}
}

@inproceedings{hai2016analysis,
 author = {Van Hai Do and Nancy F. Chen and Boon Pang Lim and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2016-736},
 keywords = {analysis},
 pages = {3863--3867},
 title = {Analysis of Mismatched Transcriptions Generated by Humans and Machines for Under-Resourced Languages},
 year = {2016}
}

@article{kong2016performance,
 author = {Xiang Kong and Preethi Jyothi and Mark Hasegawa-Johnson},
 doi = {10.1016/j.procs.2016.04.026},
 grant = {DARPA LORELEI},
 journal = {Procedia Computer Science},
 keywords = {analysis},
 pages = {30-36},
 title = {Performance Improvement of Probabilistic Transcriptions with Language-specific Constraints.},
 url = {http://www.sciencedirect.com/science/article/pii/S1877050916300400},
 volume = {81},
 year = {2016}
}

@inproceedings{varshney2016language,
 author = {Lav Varshney and Preethi Jyothi and Mark Hasegawa-Johnson},
 booktitle = {Workshop on Information Theory and Applications},
 doi = {10.1109/ITA.2016.7888198},
 grant = {NSF 1550145},
 keywords = {analysis},
 title = {Language Coverage for Mismatched Crowdsourcing},
 year = {2016}
}

@inproceedings{chang2016positive-unlabeled,
 author = {Shiyu Chang and Yang Zhang and Jiliang Tang and Dawei Lin and Yi Chang and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {KDD},
 keywords = {intelligence},
 pages = {755-764},
 title = {Positive-Unlabeled Learning in Streaming Networks},
 url = {http://www.kdd.org/kdd2016/subtopic/view/positive-unlabeled-learning-in-streaming-networks},
 year = {2016}
}

@inproceedings{yeh2016stable,
 author = {Raymond Yeh and Mark Hasegawa-Johnson and Minh Do},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2016.7472158},
 keywords = {intelligence},
 pages = {2652-2656},
 title = {Stable and Symmetric Filter Convolutional Neural Network},
 year = {2016}
}

@inproceedings{das2016an,
 author = {Amit Das and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2016-655},
 keywords = {recognition},
 pages = {3858--3862},
 software = {https://github.com/irrawaddy28/interspeech16-mtl},
 title = {An investigation on training deep neural networks using probabilistic transcription},
 year = {2016}
}

@inproceedings{das2016automatic,
 author = {Amit Das and Preethi Jyothi and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2016-657},
 keywords = {recognition},
 pages = {3524--3528},
 software = {https://github.com/irrawaddy28/africanpaper},
 title = {Automatic speech recognition using probabilistic transcriptions in Swahili, Amharic and Dinka},
 year = {2016}
}

@inproceedings{liu2016adapting,
 author = {Chunxi Liu and Preethi Jyothi and Hao Tang and Vimal Manohar and Rose Sloan and Tyler Kekona and Mark Hasegawa-Johnson and Sanjeev Khudanpur},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2016.7472797},
 keywords = {recognition},
 pages = {5840-5844},
 title = {Adapting ASR for Under-Resourced Languages Using Mismatched Transcriptions},
 year = {2016}
}

@inproceedings{qian2016application,
 author = {Kaizhi Qian and Yang Zhang and Mark Hasegawa-Johnson},
 booktitle = {Speech Prosody},
 doi = {10.21437/SpeechProsody.2016-229},
 keywords = {recognition},
 pages = {1114--1118},
 title = {Application of Local Binary Patterns for SVM based Stop Consonant Detection},
 year = {2016}
}

@inproceedings{chen2016clustering-based,
 author = {Wenda Chen and Mark Hasegawa-Johnson and Nancy Chen and Preethi Jyothi and Lav Varshney},
 booktitle = {WSSAP (Workshop on South and Southeast Asian Natural Language Processing)},
 keywords = {recognition},
 pages = {133-141},
 title = {Clustering-based Phonetic Projection in Mismatched Crowdsourcing Channels for Low-resourced ASR},
 url = {https://www.aclweb.org/anthology/W16-3714/},
 year = {2016}
}

@inproceedings{wang2016use,
 author = {Ruobai Wang and Yang Zhang and Zhijian Ou and Mark Hasegawa-Johnson},
 booktitle = {IEEE Workshop on Statistical Signal Processing},
 doi = {10.1109/SSP.2016.7551748},
 keywords = {synthesis},
 title = {Use of Particle Filtering and MCMC for Inference in Probabilistic Acoustic Tube Model},
 year = {2016}
}

@article{paine2016fast,
 author = {Paine, Tom Le and Khorrami, Pooya and Chang, Shiyu and Zhang, Yang and Ramachandran, Prajit and Hasegawa-Johnson, Mark A and Huang, Thomas S},
 journal = {arXiv preprint arXiv:1611.09482},
 keywords = {synthesis},
 title = {Fast wavenet generation algorithm},
 url = {https://arxiv.org/abs/1611.09482},
 year = {2016}
}

@phdthesis{bharadwaj2015theory,
 author = {Sujeeth Bharadwaj},
 keywords = {recognition},
 month = {June},
 school = {University of Illinois},
 title = {A theory of (almost) zero resource speech recognition},
 url = {https://www.ideals.illinois.edu/items/79584},
 year = {2015}
}

@phdthesis{huang2015shallow,
 author = {Po-Sen Huang},
 keywords = {audio},
 month = {January},
 school = {University of Illinois},
 title = {Shallow and deep learning for audio and natural language processing},
 url = {https://www.ideals.illinois.edu/items/79707},
 year = {2015}
}

@inproceedings{pietrowicz2015acoustic,
 author = {Mary Pietrowicz and Mark Hasegawa-Johnson and Karrie Karahalios},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2015-738},
 keywords = {analysis},
 pages = {3720--3724},
 title = {Acoustic Correlates for Perceived Effort Levels in Expressive Speech},
 year = {2015}
}

@inproceedings{zhang2015multichannel,
 author = {Yang Zhang and Nasser Nasrabadi and Mark Hasegawa-Johnson},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2015.7178294},
 grant = {ARO W911NF-09-1-0383},
 keywords = {analysis},
 pages = {2591:1--5},
 title = {Multichannel Transient Acoustic Signal Classification Using Task-Driven Dictionary with Joint Sparsity and Beamforming},
 year = {2015}
}

@phdthesis{abunasser2015computational,
 author = {Mahmoud Abunasser},
 keywords = {analysis},
 school = {University of Illinois},
 title = {Computational Measures of Linguistic Variation: A Study of Arabic Varieties},
 url = {https://www.ideals.illinois.edu/items/79587},
 year = {2015}
}

@inproceedings{das2015cross-lingual,
 author = {Amit Das and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2015-700},
 keywords = {recognition},
 pages = {3531--3535},
 title = {Cross-lingual transfer learning during supervised training in low resource scenarios},
 year = {2015}
}

@inproceedings{jyothi15_interspeech,
 author = {Preethi Jyothi and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2015},
 doi = {10.21437/Interspeech.2015-584},
 pages = {2774--2778},
 title = {Transcribing continuous speech using mismatched crowdsourcing},
 year = {2015}
}

@inproceedings{jyothi2015improving,
 author = {Preethi Jyothi and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2015-637},
 keywords = {recognition},
 pages = {3164--3168},
 title = {Improving Hindi Broadcast ASR by Adapting the Language Model and Pronunciation Model Using A Priori Syntactic and Morphophonemic Knowledge},
 year = {2015}
}

@unpublished{hasegawajohnson2015probabilistic,
 author = {Mark Hasegawa-Johnson and Ed Lalor and KC LEe and Preethi Jyothi and Majid Mirbagheri and Amit Das and Giovannie Di Liberto and Brad Ekin and Chunxi Liu and Vimal Manohar and Hao Tang and Paul Hager and Tyler Kekona and Rose Sloan},
 keywords = {recognition},
 note = {WS15 Group Final Presentation},
 title = {Probabilistic Transcription},
 year = {2015}
}

@inproceedings{jyothi2015transcribing,
 author = {Preethi Jyothi and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2015-584},
 keywords = {recognition},
 pages = {2774-2778},
 title = {Transcribing Continuous Speech Using Mismatched Crowdsourcing},
 year = {2015}
}

@article{hasegawajohnson2015models,
 author = {Mark Hasegawa-Johnson and Jennifer Cole and Preethi Jyothi and Lav Varshney},
 doi = {10.1515/lp-2015-0012},
 journal = {Journal of Laboratory Phonology},
 keywords = {recognition},
 number = {3-4},
 pages = {381-431},
 title = {Models of Dataset Size, Question Design, and Cross-Language Speech Perception for Speech Crowdsourcing Applications},
 volume = {6},
 year = {2015}
}

@inproceedings{jyothi2015acquiring,
 author = {Preethi Jyothi and Mark Hasegawa-Johnson},
 booktitle = {Proc. AAAI},
 doi = {10.1609/aaai.v29i1.9343},
 keywords = {recognition},
 pages = {1263-1269},
 title = {Acquiring Speech Transcriptions Using Mismatched Crowdsourcing},
 year = {2015}
}

@inproceedings{ren2015classtranscribe:,
 author = {Jia-Chen Ren and Lawrence Angrave and Mark Hasegawa-Johnson},
 booktitle = {SLaTE (the Workshop on Speech and Language Technology in Education)},
 keywords = {recognition},
 title = {ClassTranscribe: A New Tool with New Educational Opportunities for Student Crowdsourced College Lecture Transcriptions},
 url = {https://www.isca-speech.org/archive/slate_2015/ren15_slate.html},
 year = {2015}
}

@inproceedings{chen2015classtranscribe,
 author = {Jia Chen Ren and Mark Hasegawa-Johnson and Lawrence Angrave},
 booktitle = {ICER Conference},
 keywords = {recognition},
 title = {ClassTranscribe},
 year = {2015}
}

@inproceedings{zhang2015incorporating,
 author = {Yang Zhang and Zhijian Ou and Mark Hasegawa-Johnson},
 booktitle = {Proc. WASPAA},
 doi = {10.1109/WASPAA.2015.7336905},
 keywords = {synthesis},
 title = {Incorporating AM-FM effect in voiced speech for probabilistic acoustic tube model},
 year = {2015}
}

@article{huang2015joint,
 author = {Po-Sen Huang and Minje Kim and Mark Hasegawa-Johnson and Paris Smaragdis},
 doi = {10.1109/TASLP.2015.2468583},
 journal = {IEEE Trans. Audio, Speech and Language Processing},
 keywords = {synthesis},
 number = {12},
 pages = {2136-2147},
 title = {Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation},
 url = {https://arxiv.org/abs/1502.04149},
 volume = {23},
 year = {2015}
}

@inproceedings{azevedo2015improving,
 author = {Renato F. L. Azevedo and Daniel Morrow and Mark Hasegawa-Johnson and Kuangxiao Gu and Dan Soberal and Thomas Huang and William Schuh  and Rocio Garcia-Retamero},
 booktitle = {Human Factors Conference},
 grant = {AHRQ R21HS022948},
 keywords = {synthesis},
 title = {Improving Patient Comprehension of Numeric Health Information},
 year = {2015}
}

@mastersthesis{yang2015machine,
 author = {Xuesong Yang},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Machine learning approaches to improving mispronunciation detection on an imbalanced corpus},
 url = {https://www.ideals.illinois.edu/items/91251},
 year = {2015}
}

@mastersthesis{zhang2015probabilistic,
 author = {Yang Zhang},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Probabilistic Generative Modeling of Speech},
 url = {https://www.ideals.illinois.edu/items/91207},
 year = {2015}
}

@misc{hasegawa-johnson2014probabilistic,
 author = {Mark Hasegawa-Johnson},
 howpublished = {United States Patent Number 8727991},
 keywords = {analysis},
 month = {May},
 title = {Probabilistic Segmental Model For Doppler Ultrasound Heart Rate Monitoring},
 url = {http://www.google.com/patents/US8727991},
 year = {2014}
}

@unpublished{qian2014regularized,
 author = {Kaizhi Qian},
 keywords = {analysis},
 note = {B.S. Thesis, University of Illinois},
 title = {Regularized Estimation of Gaussian Mixture Models for SVM Based Speaker Recognition},
 url = {https://www.ideals.illinois.edu/items/55611},
 year = {2014}
}

@article{chen2013mixed,
 author = {Austin Chen and Mark Hasegawa-Johnson},
 doi = {10.1109/TASLP.2014.2359628},
 grant = {QNRF NPRP 09-410-1-069},
 journal = {IEEE Trans. Speech and Audio Processing},
 keywords = {analysis},
 number = {12},
 pages = {2025-2033},
 title = {Mixed Stereo Audio Classification Using a Stereo-Input Mixed-to-Panned Level Feature},
 volume = {22},
 year = {2014}
}

@inproceedings{jyothi2014an,
 author = {Preethi Jyothi and Jennifer Cole and Mark Hasegawa-Johnson and Vandana Puri},
 booktitle = {Proceedings of Speech Prosody},
 doi = {10.21437/SpeechProsody.2014-113},
 grant = {QNRF 09-410-1-069},
 keywords = {analysis},
 title = {An Investigation of Prosody in Hindi Narrative Speech},
 year = {2014}
}

@inproceedings{bharadwaj2014a,
 author = {Sujeeth Bharadwaj and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of CoLing},
 grant = {NSF 0941268},
 keywords = {intelligence},
 pages = {130-140},
 title = {A PAC-Bayesian Approach to Minimum Perplexity Language Modeling},
 url = {https://aclanthology.org/C14-1014.pdf},
 year = {2014}
}

@inproceedings{lin2014foreground,
 author = {Kai-Hsiang Lin and Pooya Khorrami and Jiangping Wang and Mark Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {Proceedings of ICIP},
 doi = {10.1109/ICIP.2014.7025224},
 keywords = {intelligence},
 pages = {1125-1129},
 title = {Foreground Object Detection in Highly Dynamic Scenes Using Saliency},
 year = {2014}
}

@inproceedings{wang2014active,
 author = {Zhaowen Wang and Zhangyang Wang and Mark Moll and Po-Sen Huang and Devin Grady and Nasser Nasrabadi and Thomas Huang and Lydia Kavraki and Mark Hasegawa-Johnson},
 booktitle = {CVPR Multi-Sensor Fusion Workshop},
 grant = {ARO W911NF-09-1-0383},
 keywords = {intelligence},
 pages = {740-747},
 title = {Active Planning, Sensing and Recognition Using a Resource-Constrained Discriminant POMDP},
 url = {https://www.cv-foundation.org/openaccess/content_cvpr_workshops_2014/W19/html/Wang_Active_Planning_Sensing_2014_CVPR_paper.html},
 year = {2014}
}

@inproceedings{jyothi14_speechprosody,
 author = {Preethi Jyothi and Jennifer Cole and Mark Hasegawa-Johnson and Vandana Puri},
 booktitle = {Proc. Speech Prosody 2014},
 doi = {10.21437/SpeechProsody.2014-113},
 pages = {623--627},
 title = {An Investigation of Prosody in Hindi Narrative Speech},
 year = {2014}
}

@inproceedings{chen2014an,
 author = {Xiayu Chen and Yang Zhang and Mark Hasegawa-Jonson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2014-191},
 keywords = {recognition},
 pages = {2327--2331},
 title = {An iterative approach to decision tree training for context dependent speech synthesis},
 year = {2014}
}

@inproceedings{khasanova14_interspeech,
 author = {Alina Khasanova and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2014},
 doi = {10.21437/Interspeech.2014-241},
 pages = {925--929},
 title = {Detecting articulatory compensation in acoustic data through linear regression modeling},
 year = {2014}
}

@inproceedings{elmahdy2014automatic,
 address = {Reykjavik, Iceland},
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 booktitle = {The 9th edition of the Language Resources and Evaluation Conference (LREC 2014)},
 grant = {QNRF NPRP 09-410-1-069},
 isbn = {9782951740884},
 keywords = {recognition},
 title = {Automatic Long Audio Alignment and Confidence Scoring for Conversational Arabic Speech},
 url = {http://www.lrec-conf.org/proceedings/lrec2014/pdf/434_Paper.pdf},
 year = {2014}
}

@inproceedings{elmahdy000038development,
 address = {Reykjavik, Iceland},
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 booktitle = {The 9th edition of the Language Resources and Evaluation Conference (LREC 2014)},
 grant = {QNRF NPRP 09-410-1-069},
 isbn = {9782951740884},
 keywords = {recognition},
 pages = {3057-3061},
 title = {Development of a TV Broadcasts Speech Recognition System for Qatari Arabic},
 url = {http://www.lrec-conf.org/proceedings/lrec2014/pdf/430_Paper.pdf},
 year = {2014}
}

@unpublished{yeh2014divergence,
 author = {Raymond Yeh},
 keywords = {recognition},
 note = {B.S. Thesis, University of Illinois},
 title = {Divergence Guided Two Beams Viterbi Algorithm on Factorial HMMs},
 url = {https://www.ideals.illinois.edu/items/55775},
 year = {2014}
}

@inproceedings{zhang2014improvement,
 author = {Yang Zhang and Zhijian Ou and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2014.6855144},
 keywords = {synthesis},
 title = {Improvement of Probabilistic Acoustic Tube Model for Speech Decomposition},
 year = {2014}
}

@inproceedings{huang2014deep,
 author = {Po-Sen Huang and Minje Kim and Paris Smaragdis and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2014.6853860},
 grant = {ARO W911NF-09-1-0383},
 keywords = {synthesis},
 title = {Deep Learning for Monaural Speech Separation},
 year = {2014}
}

@inproceedings{huang2014singing-voice,
 author = {Po-Sen Huang and Minje Kim and Mark Hasegawa-Johnson and Paris Smaragdis},
 booktitle = {Proceedings of ISMIR},
 keywords = {synthesis},
 title = {Singing-Voice Separation From Monaural Recordings Using Deep Recurrent Neural Networks},
 url = {https://archives.ismir.net/ismir2014/paper/000154.pdf},
 year = {2014}
}

@mastersthesis{soberal2014face,
 author = {Daniel Soberal},
 keywords = {multimodal},
 school = {University of Illinois},
 title = {Face recognition using hidden Markov model supervectors},
 url = {https://www.ideals.illinois.edu/items/73028},
 year = {2014}
}

@unpublished{qian2014regularized,
 author = {Kaizhi Qian},
 note = {Unpublished B.S. Thesis},
 school = {University of Illinois},
 title = {Regularized Estimation of Gaussian Mixture Models for SVM Based Speaker Recognition},
 url = {https://www.ideals.illinois.edu/items/55611},
 year = {2014}
}

@unpublished{jones2014english,
 author = {Jonathan Jones},
 note = {Unpublished B.S. Thesis},
 school = {University of Illinois},
 title = {English-Spanish Language Transfer for Automatic Speech Recognition},
 url = {https://www.ideals.illinois.edu/items/55442},
 year = {2014}
}

@mastersthesis{chen2014automatic,
 author = {Austin Chen},
 keywords = {analysis},
 school = {University of Illinois},
 title = {Automatic Classification of Electronic Music and Speech/Music Audio Content},
 url = {https://www.ideals.illinois.edu/items/49620},
 year = {2014}
}

@article{sharma2012csl,
 author = {Harsh Vardhan Sharma and Mark Hasegawa-Johnson},
 doi = {10.1016/j.csl.2012.10.002},
 journal = {Computer Speech and Language},
 keywords = {recognition},
 month = {September},
 number = {6},
 pages = {1147–1162},
 title = {Acoustic Model Adaptation using in-domain Background Models for Dysarthric Speech Recognition},
 volume = {27},
 year = {2013}
}

@inproceedings{benmamoun2013how,
 address = {Ifrane, Morocco},
 author = {Elabbas Benmamoun and Mark Hasegawa-Johnson},
 booktitle = {6th Annual Arabic Linguistics Symposium},
 isbn = {9789027236180},
 keywords = {analysis},
 month = {June},
 title = {How Different are Arabic Dialects from Each Other and from Classical Arabic},
 year = {2013}
}

@article{mertens2013on,
 author = {Robert Mertens and Po-Sen Huang and Luke Gottlieb and Gerald Friedland and Ajay Divakaran and Mark Hasegawa-Johnson},
 doi = {10.4018/jmdem.2012070101},
 journal = {International Journal of Multimedia Data Engineering and Management (IJDEM)},
 keywords = {analysis},
 month = {April},
 number = {3},
 pages = {1--19},
 title = {On the Application of Speaker Diarization to Audio Indexing of Non-Speech and Mixed Non-Speech/Speech Video Soundtracks},
 volume = {3},
 year = {2013}
}

@article{lin2013saliency-maximized,
 author = {Kai-Hsiang Lin and Xiaodan Zhuang and Camille Goudeseune and Sarah King and Mark Hasegawa-Johnson and Thomas S. Huang},
 doi = {10.1145/2536764.2536773},
 grant = {NSF 0807329},
 journal = {ACM Transactions on Applied Perception},
 keywords = {analysis},
 title = {Saliency-Maximized Audio Visualization and Efficient Audio-Visual Browsing for Faster-than-Real-Time Human Acoustic Event Detection},
 year = {2013}
}

@inproceedings{andrew2013using,
 address = {Lyon, France},
 author = {Galen Andrew and Raman Arora and Sujeeth Bharadwaj and Jeff Bilmes and Mark Hasegawa-Johnson and Karen Livescu},
 booktitle = {Proc. Workshop on Speech Production in Automatic Speech Recognition},
 keywords = {analysis},
 title = {Using articulatory measurements to learn better acoustic features},
 url = {https://www.isca-speech.org/archive/spasr_2013/andrew13_spasr.html},
 year = {2013}
}

@inproceedings{juneja2013experiments,
 address = {Lyon, France},
 author = {Amit Juneja and Mark Hasegawa-Johnson},
 booktitle = {Proc. Workshop on Speech Production in Automatic Speech Recognition},
 keywords = {analysis},
 title = {Experiments on context-awareness and phone error propagation in human and machine speech recognition},
 url = {https://www.isca-speech.org/archive/spasr_2013/juneja13_spasr.html},
 year = {2013}
}

@article{kim2013automatic,
 author = {Kyungtae Kim and Kai-Hsiang Lin and Dirk B Walther and Mark A Hasegawa-Johnson and Thomas S Huang},
 doi = {10.1016/j.patrec.2013.11.010},
 grant = {NSF 0803219},
 journal = {Pattern Recognition Letters},
 keywords = {analysis},
 number = {1},
 pages = {78-85},
 title = {Automatic Detection of Auditory Salience with Optimized Linear Filters Derived from Human Annotation},
 volume = {38},
 year = {2013}
}

@inproceedings{elmahdy2013transfer,
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 booktitle = {Workshop on Less Resourced Languages, new technologies, new challenges and opportunities (LTC 2013)},
 grant = {QNRF NPRP 09-410-1-069},
 keywords = {recognition},
 pages = {60-64},
 title = {A Transfer Learning Approach for Under-Resourced Arabic Dialects Speech Recognition},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=a7e6a76e0c1f39171c2603657a94c8ba4418a788},
 year = {2013}
}

@inproceedings{elmahdy2013automatic,
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 booktitle = {Qatar Foundation Annual Research Conference},
 doi = {10.5339/qfarf.2013.ICTP-03},
 keywords = {recognition},
 title = {Automatic Long Audio Alignment for Conversational Arabic Speech},
 year = {2013}
}

@inproceedings{elmahdy2013development,
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 booktitle = {Qatar Foundation Annual Research Conference},
 doi = {10.5339/qfarf.2013.ICTP-053},
 keywords = {recognition},
 title = {Development of a Spontaneous Large Vocabulary Speech Recognition System for Qatari Arabic},
 year = {2013}
}

@inproceedings{elmahdy2013framework,
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 booktitle = {Proc. 6th Language and Technology Conference (LTC 2013)},
 grant = {QNRF NPRP 09-410-1-069},
 keywords = {recognition},
 pages = {290-293},
 title = {A Framework for Conversational Arabic Speech Long Audio Alignment},
 url = {https://www.academia.edu/download/33424750/ltc-066-mohamed.pdf},
 year = {2013}
}

@inproceedings{bharadwaj2013sparse,
 author = {Sujeeth Bharadwaj and Mark Hasegawa-Johnson and Jitendra Ajmera and Om Deshmukh and Ashish Verma},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2013.6638228},
 keywords = {recognition},
 title = {Sparse Hidden Markov Models for Purer Clusters},
 year = {2013}
}

@inproceedings{king2013accurate,
 author = {Sarah King and Mark Hasegawa-Johnson},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2013.6639242},
 grant = {NSF 0807329},
 keywords = {recognition},
 title = {Accurate Speech Segmentation by Mimicking Human Auditory Processing},
 year = {2013}
}

@inproceedings{huang2013random,
 author = {Po-Sen Huang and Li Deng and Mark Hasegawa-Johnson and Xiaodong He},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2013.6638237},
 keywords = {recognition},
 pages = {8096--8900},
 title = {Random Features for Kernel Deep Convex Network},
 year = {2013}
}

@inproceedings{abunasser2013pronunciation,
 address = {Qatar University},
 author = {Mahmoud Abunasser and Abbas Benmamoun and Mark Hasegawa-Johnson},
 booktitle = {AIDA 10 (Association Internationale de Dialectologie Arabe)},
 keywords = {recognition},
 title = {Pronunciation Variation Metric for Four Dialects of Arabic},
 year = {2013}
}

@article{rong2012relationship,
 author = {Panying Rong and Torrey Loucks and Heejin Kim and Mark Hasegawa-Johnson},
 doi = {10.3109/02699206.2012.706686},
 journal = {Clinical Linguistics and Phonetics},
 keywords = {analysis},
 month = {September},
 number = {9},
 pages = {806-822},
 title = {Relationship between kinematics, F2 slope and speech intelligibility in dysarthria due to cerebral palsy},
 volume = {26},
 year = {2012}
}

@unpublished{hasegawa-johnson2012toward,
 author = {Mark Hasegawa-Johnson and Xiaodan Zhuang and Xi Zhou and Camille Goudeseune and Hao Tang and Kai-Hsiang Lin and Mohamed Omar and Thomas Huang},
 keywords = {analysis},
 month = {May},
 note = {Unpublished presentation given at Seoul National University},
 title = {Toward Better Real-world Acoustic Event Detection},
 year = {2012}
}

@article{mathur2012detecting,
 author = {Shobhit Mathur and Marshall Scott Poole and Feniosky Pena-Mora and Mark Hasegawa-Johnson and Noshir Contractor},
 doi = {10.1016/j.socnet.2012.04.002},
 grant = {NSF 0941268},
 journal = {Social Networks},
 keywords = {analysis},
 title = {Detecting interaction links in a collaborating group using manually annotated data},
 year = {2012}
}

@article{tang2012partially,
 author = {Hao Tang and Stephen Chu and Mark Hasegawa-Johnson and Thomas Huang},
 doi = {10.1109/TPAMI.2011.174},
 journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
 keywords = {analysis},
 number = {5},
 pages = {959-971},
 title = {Partially Supervised Speaker Clustering},
 volume = {34},
 year = {2012}
}

@inproceedings{sakr2012topic,
 author = {Ali Sakr and Mark Hasegawa-Johnson},
 booktitle = {CITALA},
 grant = {QNRF NPRP 410-1-069},
 isbn = {978-9954-9135-0-5},
 keywords = {analysis},
 pages = {153-158},
 title = {Topic Modeling of Phonetic Latin-Spelled Arabic for the Relative Analysis of Genre-Dependent and Dialect-Dependent Variation},
 url = {https://www.academia.edu/download/86879040/06fr-rist20-2.pdf},
 year = {2012}
}

@inproceedings{huang2012opportunistic,
 author = {Po-Sen Huang and Mark Hasegawa-Johnson and Wotao Yin and Tom Huang},
 booktitle = {IEEE Workshop on Machine Learning in Signal Processing},
 doi = {10.1109/MLSP.2012.6349815},
 keywords = {analysis},
 title = {Opportunistic Sensing: Unattended Acoustic Sensor Selection Using Crowdsourcing Models},
 year = {2012}
}

@inproceedings{huang2012pooling,
 author = {Po-Sen Huang and Jianchao Yang and Mark Hasegawa-Johnson and Feng Liang and Thomas S. Huang},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2012-652},
 keywords = {analysis},
 pages = {2518--2521},
 title = {Pooling Robust Shift-Invariant Sparse Representations of Acoustic Signals},
 year = {2012}
}

@inproceedings{huang2012how,
 author = {Po-Sen Huang and Robert Mertens and Ajay Divakaran and Gerald Friedland and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2012.6287927},
 grant = {ARO W911NF-09-1-0383},
 keywords = {analysis},
 title = {How to Put it into Words---Using Random Forests to Extract Symbol Level Descriptions from Audio Content for Concept Detection},
 year = {2012}
}

@inproceedings{goudeseune2012effective,
 author = {Camille Goudeseune},
 booktitle = {ACM International Workshop on Interactive Multimedia on Mobile and Portable Devices},
 doi = {10.1145/2390821.2390831},
 grant = {NSF 0807329},
 keywords = {analysis},
 software = {https://github.com/camilleg/timeliner/blob/master/README.md},
 title = {Effective browsing of long audio recordings},
 year = {2012}
}

@inproceedings{lin2012improving,
 author = {Kai-Hsiang Lin and Xiaodan Zhuang and Camille Goudeseune and Sarah King and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2012.6288368},
 grant = {NSF 0807329},
 keywords = {analysis},
 pages = {2277-2280},
 title = {Improving Faster-than-Real-Time Human Acoustic Event Detection by Saliency-Maximized Audio Visualization},
 year = {2012}
}

@article{nam2015a,
 author = {Hosung Nam and Vikramjit Mitra and Mark Tiede and Mark Hasegawa-Johnson and Carol Espy-Wilson and Elliot Saltzman and Louis Goldstein},
 doi = {10.1121/1.4763545},
 journal = {J. Acoustical Society of America},
 keywords = {analysis},
 number = {6},
 pages = {3980-3989},
 title = {A procedure for estimating gestural scores from speech acoustics},
 volume = {132},
 year = {2012}
}

@inproceedings{mahrt2012accounting,
 author = {Tim Mahrt and Jennifer Cole and Margaret Fleck and Mark Hasegawa-Johnson},
 booktitle = {Speech Prosody},
 grant = {NSF 0703624},
 keywords = {analysis},
 title = {Accounting for Speaker Variation in the Production of Prominence using the Bayesian Information Criterion},
 url = {https://www.isca-speech.org/archive/speechprosody_2012/mahrt12_speechprosody.html},
 year = {2012}
}

@inproceedings{mahrt12_interspeech,
 author = {Tim Mahrt and Jennifer Cole and Margaret Fleck and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2012},
 doi = {10.21437/Interspeech.2012-634},
 pages = {2422--2425},
 title = {F0 and the perception of prominence},
 year = {2012}
}

@inproceedings{hasegawajohnson12_speechprosody,
 author = {Mark Hasegawa-Johnson and Elabbas Benmamoun and Eiman Mustafawi and Mohamed Elmahdy and Rehab Duwairi},
 booktitle = {Proc. Speech Prosody 2012},
 pages = {159--162},
 title = {On the definition of the word “segmental”},
 url = {https://www.isca-speech.org/archive/speechprosody_2012/hasegawajohnson12_speechprosody.html},
 year = {2012}
}

@inproceedings{elmahdy2012a,
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 booktitle = {Proceedings of ESOLEC},
 grant = {QNRF NPRP 410-1-069},
 keywords = {recognition},
 title = {A Baseline Speech Recognition System for Levantine Colloquial Arabic},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=0dae1d58dddf914a9aed367e4a8045213e4202d5},
 year = {2012}
}

@inproceedings{huang2012cross-dialectal,
 author = {Po-Sen Huang and Mark Hasegawa-Johnson},
 booktitle = {International Conference on Arabic Language Processing CITALA},
 grant = {QNRF NPRP 410-1-069},
 isbn = {978-9954-9135-0-5},
 keywords = {recognition},
 pages = {119-122},
 title = {Cross-Dialectal Data Transferring for Gaussian Mixture Model Training in Arabic Speech Recognition},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=5d995e455f1f08c0032b71fd7f0bcd1dcde5786b},
 year = {2012}
}

@phdthesis{huang2012semi-supervised,
 author = {Jui-Ting Huang},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Semi-Supervised Learning for Acoustic and Prosodic Modeling in Speech Applications},
 url = {https://www.ideals.illinois.edu/items/32271},
 year = {2012}
}

@inproceedings{king2012detection,
 author = {Sarah King and Mark Hasegawa-Johnson},
 booktitle = {CoLing},
 grant = {QNRF NPRP 09-410-1-069},
 keywords = {recognition},
 pages = {589--598},
 title = {Detection of Acoustic-Phonetic Landmarks in Mismatched Conditions Using a Biomimetic Model of Human Auditory Processing},
 url = {https://aclanthology.org/C12-2058.pdf},
 year = {2012}
}

@inproceedings{hasegawajohnson2012on,
 author = {Mark Hasegawa-Johnson and Elabbas Benmamoun and Eiman Mustafawi and Mohamed Elmahdy and Rehab Duwairi},
 booktitle = {Speech Prosody},
 isbn = {978-7-5608-486-3},
 keywords = {recognition},
 pages = {159-162},
 title = {On The Definition of the Word `Segmental'},
 url = {https://www.isca-speech.org/archive/speechprosody_2012/hasegawajohnson12_speechprosody.html},
 year = {2012}
}

@article{elmahdy2012ijcl,
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 grant = {QNRF NPRP 09-410-1-069},
 issn = {2180-1266},
 journal = {International Journal of Computational Linguistics},
 keywords = {recognition},
 number = {1},
 pages = {88-96},
 title = {Hybrid Phonemic and Graphemic Modeling for Arabic Speech Recognition},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=78b19225125b6be20ed942ea380ed7d8657c71dd},
 volume = {3},
 year = {2012}
}

@inproceedings{elmahdy2012qnrf,
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi},
 booktitle = {Qatar Foundation Annual Research Forum},
 doi = {10.5339/qfarf.2012.CSO3},
 grant = {QNRF 09-410-1-069},
 keywords = {recognition},
 title = {Hybrid Pronunciation Modeling for Arabic Large Vocabulary Speech Recognition},
 year = {2012}
}

@inproceedings{bharadwaj2012multi-view,
 author = {Sujeeth Bharadwaj and Raman Arora and Karen Livescu and Mark Hasegawa-Johnson},
 booktitle = {IWSML (Internat. Worksh. on Statistical Machine Learning for Sign. Process.)},
 grant = {NSF 0905633},
 keywords = {recognition},
 title = {Multi-View Acoustic Feature Learning Using Articulatory Measurements},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=2106a2dce0f7c3ea611499ed93187dcee841fc16},
 year = {2012}
}

@unpublished{hasegawajohnson2012transfer,
 author = {Mark Hasegawa-Johnson and David Harwath and Harsh Vardhan Sharma and Po-Sen Huang},
 booktitle = {presentation given at the 2012 Urbana Neuroengineering Conference},
 keywords = {recognition},
 title = {Transfer Learning for Multi-Person and Multi-Dialect Spoken Language Interface},
 year = {2012}
}

@phdthesis{sharma2012thesis,
 author = {Harsh Vardhan Sharma},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Acoustic Model Adaptation for Recognition of Dysarthric Speech},
 url = {https://www.ideals.illinois.edu/items/32231},
 year = {2012}
}

@inproceedings{huang2012singing-voice,
 author = {Po-Sen Huang and Scott Deeann Chen and Paris Smaragdis and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2012.6287816},
 grant = {ARO W911NF-09-1-0383},
 keywords = {synthesis},
 title = {Singing-Voice Separation from Monaural Recordings using Robust Principal Component Analysis},
 year = {2012}
}

@phdthesis{zhuang2011modeling,
 author = {Xiaodan Zhuang},
 keywords = {analysis},
 month = {April},
 school = {University of Illinois},
 title = {Modeling Audio and Visual Cues for Real-world Event Detection},
 url = {https://www.ideals.illinois.edu/items/24703},
 year = {2011}
}

@inproceedings{mahrt2011feature,
 author = {Tim Mahrt and Jui-Ting Huang and Yoonsook Mo and Jennifer Cole and Mark Hasegawa-Johnson and Margaret Fleck},
 booktitle = {New Tools and Methods for Very Large Scale Phonetics Research},
 keywords = {analysis},
 month = {Jan.},
 publisher = {University of Pennsylvania},
 title = {Feature Sets for the Automatic Detection of Prosodic Prominence},
 year = {2011}
}

@inproceedings{nam2011automatic,
 author = {Hosung Nam and Vikramjit Mitra and Mark Tiede and Mark Hasegawa-Johnson and Carol Espy-Wilson and Elliot Saltzman and Louis Goldstein},
 booktitle = {Workshop on New Tools and Methods for Very Large Scale Phonetics Research},
 keywords = {analysis},
 month = {Jan.},
 publisher = {University of Pennsylvania},
 title = {Automatic gestural annotation of the U. Wisconsin X-ray Microbeam corpus},
 year = {2011}
}

@inproceedings{huang2011how,
 address = {University of Pennsylvania},
 author = {Jui-Ting Huang and Mark Hasegawa-Johnson and Jennifer Cole},
 booktitle = {Workshop on New Tools and Methods for Very Large Scale Phonetics Research},
 keywords = {recognition},
 month = {Jan.},
 title = {How Unlabeled Data Change the Acoustic Models For Phonetic Classification},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=a6231219eed53704d7afb38176db1aa04705a1f6},
 year = {2011}
}

@inproceedings{kantor2011hmm-based,
 address = {University of Pennsylvania},
 author = {Arthur Kantor and Mark Hasegawa-Johnson},
 booktitle = {Workshop on New Tools and Methods for Very Large Scale Phonetics Research},
 grant = {NSF 0703624},
 keywords = {recognition},
 month = {Jan.},
 software = {http://mickey.ifp.illinois.edu/speechWiki/index.php/Phonetic_Transcription_Tool},
 title = {HMM-based Pronunciation Dictionary Generation},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=66a415c3c988807ed959fc159fd95786ee8f0029},
 year = {2011}
}

@unpublished{al-sabbagh2011using,
 author = {Rania Al-Sabbagh and Roxana Girju and Mark Hasegawa-Johnson and Elabbas Benmamoun and Rehab Duwairi and Eiman Mustafawi},
 keywords = {analysis},
 note = {Talk delivered at the Linguistics in the Gulf Conference},
 title = {Using Web Mining Techniques to Build a Multi-Dialect Lexicon of Arabic},
 year = {2011}
}

@inproceedings{mertens2011on,
 author = {R. Mertens and P.-S. Huang and L. Gottlieb and G. Friedland and A. Divakaran},
 booktitle = {IEEE International Symposium on Multimedia},
 doi = {10.1109/ISM.2011.79},
 keywords = {analysis},
 pages = {446-451},
 title = {On the Application of Speaker Diarization to Audio Concept Detection for Multimedia Retrieval},
 year = {2011}
}

@inproceedings{huang2011exemplar,
 address = {Maryland},
 author = {Po-Sen Huang and Mark Hasegawa-Johnson and Thyagaraju Damarla},
 booktitle = {Second Annual Human and Light Vehicle Detection Workshop},
 grant = {ARO W911NF-09-1-0383},
 keywords = {analysis},
 pages = {14:1-10},
 title = {Exemplar Selection Methods to Distinguish Human from Animal Footsteps},
 url = {https://posenhuang.github.io/papers/Exemplar_Selection_HLVD2011.pdf},
 year = {2011}
}

@inproceedings{huang2011multi-sensory,
 author = {Po-Sen Huang and Thyagaraju Damarla and Mark Hasegawa-Johnson},
 booktitle = {Fusion},
 grant = {ARO W911NF-09-1-0383},
 keywords = {analysis},
 title = {Multi-sensory features for Personnel Detection at Border Crossings},
 url = {https://ieeexplore.ieee.org/abstract/document/5977673?casa_token=APIqmZlnHDcAAAAA:66fMhlnUcKNXV6jKVFSz0hCDsoABgGyblOhRExzAtqjMs4XMBCJ8zPfVAnhT-yJg2Bz4rOpkfw},
 year = {2011}
}

@inproceedings{huang2011improving,
 author = {Po-Sen Huang and Xiaodan Zhuang and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2011.5946412},
 grant = {ARO W911NF-09-1-0383},
 keywords = {analysis},
 pages = {349-352},
 title = {Improving Acoustic Event Detection using Generalizable Visual Features and Multi-modality Modeling},
 year = {2011}
}

@article{kim2011temporal,
 author = {Heejin Kim and Mark Hasegawa-Johnson and Adrienne Perlman},
 doi = {10.1121/1.3654821},
 journal = {Journal of the Acoustical Society of America},
 keywords = {analysis},
 pages = {2446},
 title = {Temporal and spectral characteristics of fricatives in dysarthria},
 volume = {130},
 year = {2011}
}

@article{kim2011vowel,
 author = {Heejin Kim and Mark Hasegawa-Johnson and Adrienne Perlman},
 doi = {10.1159/000318881},
 grant = {NIH DC0032301},
 journal = {Folia Phoniatrica et Logopaedica},
 keywords = {analysis},
 number = {4},
 pages = {187-194},
 title = {Vowel Contrast and Speech Intelligibility in Dysarthria},
 volume = {63},
 year = {2011}
}

@inproceedings{mahrt2011optimal,
 author = {Tim Mahrt and Jui-Ting Huang and Yoonsook Mo and Margaret Fleck and Mark Hasegawa-Johnson and Jennifer Cole},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2011-535},
 keywords = {analysis},
 pages = {2037--2040},
 title = {Optimal models of prosodic prominence using the Bayesian information criterion},
 year = {2011}
}

@article{ozbek2011on,
 author = {İ. Yücel Ozbek and Mark Hasegawa-Johnson and Mübeccel Demirekler},
 doi = {10.1109/TASL.2011.2157496},
 journal = {IEEE Transactions on Audio, Speech, and Language},
 keywords = {analysis},
 number = {1},
 pages = {67--81},
 title = {On Improving Dynamic State Space Approaches to Articulatory Inversion with MAP based Parameter Estimation},
 volume = {20},
 year = {2011}
}

@article{ozbek2011estimation,
 author = {İ. Yücel Ozbek and Mark Hasegawa-Johnson and Mübeccel Demirekler},
 doi = {10.1109/TASL.2010.2087751},
 journal = {IEEE Transactions on Audio, Speech, and Language},
 keywords = {analysis},
 number = {5},
 pages = {1180-1195},
 title = {Estimation of Articulatory Trajectories Based on Gaussian Mixture Model (GMM) with Audio-Visual Information Fusion and Dynamic Kalman Smoothing},
 volume = {19},
 year = {2011}
}

@inproceedings{elmahdy2011challenges,
 author = {Mohamed Elmahdy and Mark Hasegawa-Johnson and Eiman Mustafawi and Rehab Duwairi and Wolfgang Minker},
 booktitle = {Qatar Foundation Annual Research Forum},
 doi = {10.5339/qfarf.2011.CSO5},
 grant = {QNRF NPRP 410-1-069},
 keywords = {recognition},
 pages = {244},
 title = {Challenges and Techniques for Dialectal Arabic Speech Recognition and Machine Translation},
 year = {2011}
}

@unpublished{hasegawajohnson2011learning,
 author = {Mark Hasegawa-Johnson and Jui-Ting Huang and Roxana Girju and Rehab Mustafa Mohamma Duwairi and Eiman Mohd Tayyeb H B Mustafawi and Elabbas Benmamoun},
 doi = {10.5339/qfarf.2011.CSP15},
 grant = {QNRF NPRP 410-1-069},
 keywords = {recognition},
 note = {Qatar Foundation Annual Research Forum},
 pages = {269},
 title = {Learning to Recognize Speech from a Small Number of Labeled Examples},
 year = {2011}
}

@article{hasegawajohnson2011normalized,
 author = {Mark Hasegawa-Johnson and Jui-Ting Huang and Sarah King and Xi Zhou},
 doi = {10.1121/1.3655075},
 grant = {NSF 0807329},
 journal = {Journal of the Acoustical Society of America},
 keywords = {recognition},
 pages = {2524},
 title = {Normalized recognition of speech and audio events},
 volume = {130},
 year = {2011}
}

@article{hasegawajohnson2011semi-supervised,
 author = {Mark Hasegawa-Johnson and Jui-Ting Huang and Xiaodan Zhuang},
 doi = {10.1121/1.3654654},
 grant = {NSF 0703624},
 journal = {Journal of the Acoustical Society of America},
 keywords = {recognition},
 pages = {2408},
 title = {Semi-supervised learning for speech and audio processing},
 volume = {130},
 year = {2011}
}

@phdthesis{pang2011computational,
 author = {Boon Pang Lim},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Computational Differences between Whispered and Non-whispered Speech},
 url = {https://www.ideals.illinois.edu/items/24896},
 year = {2011}
}

@inproceedings{hasegawajohnson2011multimodal,
 author = {Mark Hasegawa-Johnson and Camille Goudeseune and Jennifer Cole and Hank Kaczmarski and Heejin Kim and Sarah King and Timothy Mahrt and Jui-Ting Huang and Xiaodan Zhuang and Kai-Hsiang Lin and Harsh Vardhan Sharma and Zhen Li and Thomas S. Huang},
 booktitle = {APSIPA},
 grant = {NSF 0807329},
 keywords = {recognition},
 pages = {256:1-8},
 title = {Multimodal Speech and Audio User Interfaces for K-12 Outreach},
 url = {http://www.apsipa.org/proceedings_2011/pdf/APSIPA256.pdf},
 year = {2011}
}

@mastersthesis{bharadwaj2011multiview,
 author = {Sujeeth Bharadwaj},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Multiview feature learning for speech recognition},
 url = {https://www.ideals.illinois.edu/items/30027},
 year = {2011}
}

@mastersthesis{tidemann2011characterization,
 author = {Jeremy Tidemann},
 keywords = {analysis},
 school = {University of Illinois},
 title = {Characterization of the Head-Related Transfer Function using Chirp and Maximum Length Sequence Excitation Signals},
 url = {https://www.ideals.illinois.edu/items/25190},
 year = {2011}
}

@mastersthesis{huang2011non,
 author = {Po-Sen Huang},
 keywords = {multimodal},
 school = {University of Illinois},
 title = {Non-speech Acoustic Event Detection Using Multimodal Information},
 url = {https://www.ideals.illinois.edu/items/30083},
 year = {2011}
}

@article{zhuang2010real-world,
 author = {Xiaodan Zhuang and Xi Zhou and Mark A. Hasegawa-Johnson and Thomas S. Huang},
 doi = {10.1016/j.patrec.2010.02.005},
 grant = {NSF 0807329},
 journal = {Pattern Recognition Letters},
 keywords = {analysis},
 month = {Sep.},
 number = {2},
 pages = {1543-1551},
 title = {Real-world Acoustic Event Detection},
 volume = {31},
 year = {2010}
}

@phdthesis{kim2010statistical,
 author = {Lae-Hoon Kim},
 keywords = {synthesis},
 month = {August},
 school = {University of Illinois},
 title = {Statistical Model Based Multi-Microphone Speech Processing: Toward Overcoming Mismatch Problem},
 url = {http://hdl.handle.net/2142/16839},
 year = {2010}
}

@article{zhou2010novel,
 author = {Xi Zhou and Xiaodan Zhuang and Hao Tang and Mark A. Hasegawa-Johnson and Thomas S. Huang},
 doi = {10.1016/j.patrec.2009.12.010},
 grant = {NSF 0807329},
 journal = {Pattern Recognition Letters},
 keywords = {intelligence},
 month = {Jun.},
 number = {8},
 pages = {702-708},
 title = {Novel Gaussianized Vector Representation for Improved Natural Scene Categorization},
 volume = {31},
 year = {2010}
}

@inproceedings{harwath2010phonetic,
 author = {David Harwath and Mark Hasegawa-Johnson},
 booktitle = {Speech Prosody},
 grant = {NSF 0703624},
 keywords = {analysis},
 pages = {100231:1-4},
 title = {Phonetic Landmark Detection for Automatic Language Identification},
 url = {https://www.isca-speech.org/archive/speechprosody_2010/harwath10_speechprosody.html},
 year = {2010}
}

@inproceedings{bhat2010interspeech,
 author = {Suma Bhat and Mark Hasegawa-Johnson and Richard Sproat},
 booktitle = {INTERSPEECH Satellite Workshop on Second Language Studies: Acquisition, Learning, Education and Technology},
 keywords = {analysis},
 title = {Automatic Fluency Assessment by Signal-Level Measurement of Spontaneous Speech},
 url = {https://www.isca-speech.org/archive/l2ws_2010/bhat10_l2ws.html},
 year = {2010}
}

@inproceedings{yoon2010landmark-based,
 author = {Su-Youn Yoon and Mark Hasegawa-Johnson and Richard Sproat},
 booktitle = {Proceedings of Interspeech},
 doi = {10.21437/Interspeech.2010-236},
 keywords = {analysis},
 pages = {614--617},
 title = {Landmark-based Automated Pronunciation Error Detection},
 year = {2010}
}

@inproceedings{bhat2010language,
 address = {Denver, CO},
 author = {Suma Bhat and Richard Sproat and Mark Hasegawa-Johnson and Fred Davidson},
 booktitle = {Language Testing Research Colloquium},
 keywords = {analysis},
 title = {Automatic fluency assessment using thin-slices of spontaneous speech},
 year = {2010}
}

@article{kim2010frequency,
 author = {Heejin Kim and Katie Martin and Mark Hasegawa-Johnson and Adrienne Perlman},
 doi = {10.3109/02699206.2010.497238},
 grant = {NIH DC0032301},
 journal = {Clinical Linguistics & Phonetics},
 keywords = {analysis},
 number = {10},
 pages = {759-770},
 title = {Frequency of consonant articulation errors in dysarthric speech},
 url = {https://www.tandfonline.com/doi/pdf/10.3109/02699206.2010.497238?casa_token=CjxOPSE_L_IAAAAA:EenLYvmMx1Da4-Sp69jHUVHNqTjMhVHxh3-ns6KPTlVx0kUadyZLad9i_kqgnaAeWTXsUViDvvE},
 volume = {24},
 year = {2010}
}

@inproceedings{kim2010acoustic,
 author = {Heejin Kim and Mark Hasegawa-Johnson and Adrienne Perlman},
 booktitle = {Speech Prosody},
 grant = {NIH R21-DC008090-A},
 keywords = {analysis},
 pages = {100891:1-4},
 title = {Acoustic Cues to Lexical Stress in Spastic Dysarthria},
 url = {https://www.isca-speech.org/archive/speechprosody_2010/kim10_speechprosody.html},
 year = {2010}
}

@inproceedings{kim2010kinematic,
 author = {Heejin Kim and Panying Rong and Torrey M. Loucks and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of Interspeech},
 doi = {10.21437/Interspeech.2010-697},
 grant = {NSF 0534106},
 keywords = {analysis},
 pages = {2578--2581},
 title = {Kinematic Analysis of Tongue Movement Control in Spastic Dysarthria},
 year = {2010}
}

@article{lobdell2010intelligibility,
 author = {Bryce E Lobdell and Jont B Allen and Mark A Hasegawa-Johnson},
 doi = {10.1016/j.specom.2010.08.016},
 journal = {Speech Communication},
 keywords = {analysis},
 title = {Intelligibility predictors and neural representation of speech},
 year = {2010}
}

@inproceedings{mo2010prosodic,
 author = {Yoonsook Mo and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {Speech Prosody},
 grant = {NSF 0703624},
 keywords = {analysis},
 pages = {100208:1-4},
 title = {Prosodic effects on temporal structure of monosyllabic CVC words in American English},
 url = {https://www.isca-speech.org/archive/speechprosody_2010/mo10_speechprosody.html},
 year = {2010}
}

@inproceedings{tang2010non-frontal,
 author = {Hao Tang and Mark Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {ICME},
 doi = {10.1109/ICME.2010.5582576},
 keywords = {intelligence},
 pages = {1202-1207},
 title = {Non-Frontal View Facial Expression Recognition},
 year = {2010}
}

@inproceedings{huang2010prosody-dependent,
 author = {Jui-Ting Huang and Po-Sen Huang and Yoonsook Mo and Mark Hasegawa-Johnson and Jennifer Cole},
 booktitle = {Speech Prosody},
 grant = {NSF 0703624},
 keywords = {recognition},
 pages = {100623:1-4},
 title = {Prosody-Dependent Acoustic Modeling Using Variable-Parameter Hidden Markov Models},
 url = {https://www.isca-speech.org/archive/speechprosody_2010/huang10_speechprosody.html},
 year = {2010}
}

@inproceedings{tang2010toward,
 author = {Hao Tang and Mark Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2010.5494989},
 grant = {NSF 0803219},
 keywords = {recognition},
 title = {Toward Robust Learning of the Gaussian Mixture State Emission Densities for Hidden Markov Models},
 year = {2010}
}

@phdthesis{kantor2010pronunciation,
 author = {Arthur Kantor},
 keywords = {recognition},
 school = {University of Illinois},
 software = {http://mickey.ifp.illinois.edu/speechWiki/index.php/GMTK_parallel_tools},
 title = {Pronunciation modeling for large vocabulary speech recognition},
 url = {https://www.ideals.illinois.edu/items/18366},
 year = {2010}
}

@inproceedings{hu2010interspeech,
 author = {Chi Hu and Xiaodan Zhuang and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of Interspeech},
 doi = {10.21437/Interspeech.2010-624},
 grant = {NSF 0703624},
 keywords = {recognition},
 pages = {2274--2277},
 title = {FSM-Based Pronunciation Modeling using Articulatory Phonological Code},
 year = {2010}
}

@inproceedings{nam2010a,
 author = {Hosung Nam and Vikramjit Mitra and Mark Tiede and Elliot Saltzman and Louis Goldstein and Carol Espy-Wilson and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of Interspeech},
 doi = {10.21437/Interspeech.2010-4},
 grant = {NSF 0703624},
 keywords = {recognition},
 pages = {30--33},
 title = {A procedure for estimating gestural scores from natural speech},
 year = {2010}
}

@inproceedings{huang2010semi-supervised,
 author = {Jui-Ting Huang and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of Interspeech},
 doi = {10.21437/Interspeech.2008-116},
 grant = {NSF 0703624},
 keywords = {recognition},
 pages = {1353--1356},
 title = {Semi-Supervised Training of Gaussian Mixture Models by Conditional Entropy Minimization},
 year = {2010}
}

@inproceedings{sharma2010state,
 author = {Harsh Vardhan Sharma and Mark Hasegawa-Johnson},
 booktitle = {HLT/NAACL Workshop on Speech and Language Processing for Assistive Technology (SLPAT)},
 grant = {NSF 0534106},
 keywords = {recognition},
 pages = {72-79},
 title = {State Transition Interpolation and MAP Adaptation for HMM-based Dysarthric Speech Recognition},
 url = {http://delivery.acm.org/10.1145/1870000/1867763/p72-sharma.pdf?key1=1867763&key2=2798521031&coll=DL&dl=ACM&ip=65.42.208.134&CFID=15366854&CFTOKEN=94985121},
 year = {2010}
}

@inproceedings{zhuang2010a,
 author = {Xiaodan Zhuang and Lijuan Wang and Frank Soong and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of Interspeech},
 doi = {10.21437/Interspeech.2010-498},
 grant = {NSF 0703624},
 keywords = {synthesis},
 pages = {1736--1739},
 title = {A Minimum Converted Trajectory Error (MCTE) Approach to High Quality Speech-to-Lips Conversion},
 year = {2010}
}

@inproceedings{kim2010toward,
 author = {Lae-Hoon Kim and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of Asilomar},
 doi = {10.1109/ACSSC.2010.5757618},
 grant = {NSF 0913188},
 keywords = {synthesis},
 title = {Toward Overcoming Fundamental Limitation in Frequency-Domain Blind Source Separation for Reverberant Speech Mixtures},
 year = {2010}
}

@inproceedings{kim2010robust,
 author = {Lae-Hoon Kim and Kyung-Tae Kim and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of Interspeech},
 doi = {10.21437/Interspeech.2010-583},
 grant = {NSF 0913188},
 keywords = {synthesis},
 pages = {2066--2069},
 title = {Robust Automatic Speech Recognition with Decoder Oriented Ideal Binary Mask Estimation},
 year = {2010}
}

@article{kim2010speech,
 author = {Lae-Hoon Kim and Kyungtae Kim and Mark Hasegawa-Johnson},
 doi = {10.1121/1.3384190},
 journal = {J. Acoust. Soc. Am.},
 keywords = {synthesis},
 number = {3},
 pages = {1817},
 title = {Speech enhancement beyond minimum mean squared error with perceptual noise shaping},
 volume = {127},
 year = {2010}
}

@inproceedings{kim2010joint,
 author = {Lae-Hoon Kim and Mark Hasegawa-Johnson and Gerasimos Potamianos and Vit Libal},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2010.5496144},
 keywords = {synthesis},
 title = {Joint Estimation of DOA and Speech Based on EM Beamforming},
 year = {2010}
}

@mastersthesis{hu2010thesis,
 author = {Chi Hu},
 keywords = {recognition},
 school = {University of Illinois},
 title = {FSM-Based Pronunciation Modeling using Articulatory Phonological Code},
 url = {https://www.ideals.illinois.edu/items/16794},
 year = {2010}
}

@unpublished{harwath2010phonetic,
 author = {David Harwath},
 note = {Unpublished B.S. Thesis},
 school = {University of Illinois},
 title = {Phonetic Landmark Detection for Automatic Language Identification},
 url = {https://www.ideals.illinois.edu/items/47011},
 year = {2010}
}

@inproceedings{yoon2009interspeech,
 address = {Brighton},
 author = {Su-Youn Yoon and Mark Hasegawa-Johnson and Richard Sproat},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2009-551},
 keywords = {analysis},
 month = {September},
 pages = {1903--1906},
 title = {Automated Pronunciation Scoring using Confidence Scoring and Landmark-based SVM},
 year = {2009}
}

@inproceedings{ozbek2009formant,
 address = {Brighton},
 author = {I. Yücel Özbek and Mark Hasegawa-Johnson and Mübeccel Demirekler},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2009-717},
 keywords = {analysis},
 month = {September},
 pages = {2807--2810},
 title = {Formant Trajectories for Acoustic-to-Articulatory Inversion},
 year = {2009}
}

@inproceedings{mo2009prosodic,
 address = {Brighton},
 author = {Yoonsook Mo and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2009-668},
 grant = {NSF 0703624},
 keywords = {analysis},
 month = {September},
 pages = {2535--2538},
 title = {Prosodic effects on vowel production: evidence from formant structure},
 year = {2009}
}

@inproceedings{zhuang2009articulatory,
 address = {Brighton},
 author = {Xiaodan Zhuang and Hosung Nam and Mark Hasegawa-Johnson and Louis Goldstein and Elliot Saltzman},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2009-706},
 grant = {NSF 0703624},
 keywords = {recognition},
 month = {September},
 pages = {2763--2766},
 title = {Articulatory Phonological Code for Word Recognition},
 year = {2009}
}

@inproceedings{sharma2009universal,
 address = {Brighton},
 author = {Harsh Vardhan Sharma and Mark Hasegawa-Johnson and Jon Gunderson and Adrienne Perlman},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2009-444},
 grant = {NIH R21 DC008090A},
 keywords = {recognition},
 month = {September},
 pages = {1451--1454},
 title = {Universal Access: Speech Recognition for Talkers with Spastic Dysarthria},
 year = {2009}
}

@inproceedings{lee2009a,
 address = {Dallas},
 author = {Bowon Lee and Mark Hasegawa-Johnson},
 booktitle = {DSP in Cars workshop},
 keywords = {recognition},
 month = {July},
 title = {A Phonemic Restoration Approach for Automatic Speech Recognition with Highly Nonstationary Background Noise},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=66f31946db0456df7be1f6b09528e2f5be8f84e0},
 year = {2009}
}

@article{huang2009sensitive,
 author = {Thomas S. Huang and Mark A. Hasegawa-Johnson and Stephen M. Chu and Zhihong Zeng and Hao Tang},
 doi = {10.1109/MSP.2009.932562},
 journal = {IEEE Signal Processing Magazine},
 keywords = {synthesis},
 month = {July},
 number = {4},
 pages = {67-72},
 title = {Sensitive Talking Heads},
 volume = {26},
 year = {2009}
}

@inproceedings{kim2009optimal,
 address = {Dallas},
 author = {Lae-Hoon Kim and Mark Hasegawa-Johnson},
 booktitle = {DSP in Cars workshop},
 grant = {NSF 0803219},
 keywords = {synthesis},
 month = {July},
 title = {Optimal Multi-Microphone Speech Enhancement in Cars},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=f43edc454be762b15b7b023f52f406c00f695b59},
 year = {2009}
}

@inproceedings{tang2009emotion,
 author = {Hao Tang and Stephen M. Chu and Mark Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {International Conference on Multimedia & Expo (ICME'09)},
 doi = {10.1109/ICME.2009.5202493},
 grant = {NIH R21 DC008090 A},
 keywords = {analysis},
 pages = {294-297},
 title = {Emotion Recognition from Speech via Boosted Gaussian Mixture Models},
 year = {2009}
}

@inproceedings{hasegawa-johnson2009visual,
 author = {Mark Hasegawa-Johnson and Camille Goudeseune and Kai-Hsiang Lin and David Cohen and Xi Zhou and Xiaodan Zhuang and Kyungtae Kim and Hank Kaczmarski and Thomas Huang},
 booktitle = {NIPS Workshop on Visual Analytics},
 grant = {NSF 0807329},
 keywords = {analysis},
 title = {Visual Analytics for Audio},
 year = {2009}
}

@unpublished{hasegawa-johnson2009pattern,
 author = {Mark Hasegawa-Johnson},
 grant = {NSF 0807329},
 keywords = {analysis},
 note = {Unpublished presentation at the Machine Learning Summer School, University of Chicago},
 title = {Pattern Recognition in Acoustic Signal Processing},
 year = {2009}
}

@article{hasegawa-johnson2009tutorial,
 author = {Mark Hasegawa-Johnson},
 doi = {10.1121/1.4784323},
 grant = {NSF 0803219},
 journal = {J. Acoust. Soc. Am.},
 keywords = {analysis},
 pages = {2698},
 title = {Tutorial: Pattern Recognition in Signal Processing},
 volume = {125},
 year = {2009}
}

@article{hasegawa-johnson2009adaptation,
 author = {Mark Hasegawa-Johnson and Xiaodan Zhuang and Xi Zhou and Camille Goudeseune and Thomas S. Huang},
 doi = {10.1121/1.4784503},
 journal = {J. Acoust. Soc. Am.},
 keywords = {analysis},
 pages = {2730},
 title = {Adaptation of tandem HMMs for non-speech audio event detection},
 volume = {125},
 year = {2009}
}

@inproceedings{zhuang2009acoustic,
 author = {Xiaodan Zhuang and Jing Huang and Gerasimos Potamianos and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2009.4959522},
 keywords = {analysis},
 pages = {69-72},
 title = {Acoustic Fall Detection using Gaussian Mixture Models and GMM Supervectors},
 year = {2009}
}

@inproceedings{yoon2009calico,
 author = {Su-Youn Yoon and Mark Hasegawa-Johnson and Richard Sproat},
 booktitle = {CALICO workshop},
 keywords = {analysis},
 title = {Automated Pronunciation Scoring for L2 English Learners},
 year = {2009}
}

@unpublished{cohen2009efficient,
 author = {David Cohen and Camille Goudeseune and Mark Hasegawa-Johnson},
 keywords = {analysis},
 note = {Georgia Tech publication GT-FODAVA-09-01},
 software = {https://github.com/camilleg/multiscale-FFT},
 title = {Efficient Simultaneous Multi-Scale Computation of FFTs},
 year = {2009}
}

@article{yoon2009construction,
 author = {Su-Youn Yoon and Lisa Pierce and Amanda Huensch and Eric Juul and Samantha Perkins and Richard Sproat and Mark Hasegawa-Johnson},
 journal = {CALICO journal},
 keywords = {analysis},
 title = {Construction of a rated speech corpus of L2 learners' speech},
 url = {https://www.jstor.org/stable/pdf/calicojournal.26.3.662.pdf?casa_token=fCpVdyBksEoAAAAA:n5lwoOcMttFqYjtsLvYeRcIoGOzjAy5r4_XDSZc4MWe4qPQzCpKEQXnpGTRzy2SyvsLWrcrzAl4Nki-4FPSj36-NIQSqcwffDoms1tPJ8Srti9W1tQ},
 year = {2009}
}

@phdthesis{lobdell2009models,
 author = {Bryce Lobdell},
 keywords = {analysis},
 school = {University of Illinois},
 title = {Models of Human Phone Transcription in Noise Based on Intelligibility Predictors},
 url = {https://hdl.handle.net/2142/81127},
 year = {2009}
}

@article{mo2009how,
 author = {Yoonsook Mo and Jennifer Cole and Mark Hasegawa-Johnson},
 doi = {10.1121/1.4783760},
 grant = {NSF 0703624},
 journal = {J. Acoust. Soc. Am.},
 keywords = {analysis},
 number = {4},
 pages = {2572},
 title = {How do ordinary listeners perceive prosodic prominence? Syntagmatic vs. Paradigmatic comparison.},
 volume = {125},
 year = {2009}
}

@phdthesis{borys2009lovable,
 author = {Sarah Borys},
 keywords = {analysis},
 school = {University of Illinois},
 title = {Lovable Indestructible Grad Student of Chaos},
 year = {2009}
}

@inproceedings{zhuang2009efficient,
 author = {Xiaodan Zhuang and Xi Zhou and Mark A. Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {IMCE},
 doi = {10.1145/1631040.1631055},
 grant = {NSF 0803219},
 keywords = {intelligence},
 pages = {89-96},
 title = {Efficient Object Localization with Gaussianized Vector Representation},
 year = {2009}
}

@inproceedings{huang2009kernel,
 author = {Jui-Ting Huang and Xi Zhou and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {ASRU},
 doi = {10.1109/ASRU.2009.5373389},
 grant = {NSF 0703624},
 keywords = {recognition},
 pages = {141-145},
 title = {Kernel Metric Learning for Phonetic Classification},
 year = {2009}
}

@inproceedings{huang2009on,
 author = {Jui-Ting Huang and Mark Hasegawa-Johnson},
 booktitle = {NAACL HLT Workshop on Semi-Supervised Learning},
 grant = {NSF 0534106},
 keywords = {recognition},
 pages = {75-83},
 title = {On semi-supervised learning of Gaussian mixture models for phonetic classification},
 url = {https://aclanthology.org/W09-2210.pdf},
 year = {2009}
}

@inproceedings{zhuang2009speech,
 author = {Xiaodan Zhuang and Jui-Ting Huang and Mark Hasegawa-Johnson},
 booktitle = {NAACL HLT Cross-Lingual Information Access Workshop (CLIAWS)},
 grant = {NSF 0703624},
 keywords = {recognition},
 pages = {3-11},
 title = {Speech Retrieval in Unknown Languages: a Pilot Study},
 url = {https://aclanthology.org/W09-1602.pdf"},
 year = {2009}
}

@unpublished{bharadwaj2009advances,
 author = {Sujeeth Bharadwaj},
 note = {Unpublished B.S. Thesis},
 school = {University of Illinois},
 title = {Advances in Sparse Classification},
 url = {https://www.ideals.illinois.edu/items/47037},
 year = {2009}
}

@inproceedings{huang2008unsupervised,
 author = {Jui-Ting Huang and Mark Hasegawa-Johnson},
 booktitle = {SpeechProsody},
 grant = {NSF 0534133},
 keywords = {analysis},
 pages = {165-168},
 title = {Unsupervised Prosodic Break Detection in Mandarin Speech},
 url = {https://www.isca-speech.org/archive/speechprosody_2008/huang08_speechprosody.html},
 year = {2008}
}

@inproceedings{zhuang2008towards,
 author = {Xiaodan Zhuang and Mark Hasegawa-Johnson},
 booktitle = {SpeechProsody},
 grant = {NSF 0414117},
 keywords = {analysis},
 pages = {37-40},
 title = {Towards Interpretation of Creakiness in Switchboard},
 url = {https://www.isca-speech.org/archive/speechprosody_2008/zhuang08_speechprosody.html},
 year = {2008}
}

@inproceedings{yoon000019detecting,
 author = {Taejin Yoon and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {SpeechProsody},
 grant = {NSF 0414117},
 keywords = {analysis},
 pages = {33-36},
 title = {Detecting Non-Modal Phonation in Telephone Speech},
 url = {https://www.isca-speech.org/archive/speechprosody_2008/yoon08_speechprosody.html},
 year = {2008}
}

@inproceedings{yoon2008detecting,
 author = {Tae-Jin Yoon and Cole and Jennifer and Mark Hasegawa-Johnson and Chilin Shih},
 booktitle = {Proc. Speech Prosody},
 grant = {NSF 0414117},
 keywords = {analysis},
 title = {Detecting Non-modal Phonation in Telephone Speech},
 url = {https://www.isca-archive.org/speechprosody_2008/yoon08_speechprosody.pdf},
 year = {2008}
}

@inproceedings{zhuang000070feature,
 author = {Xiaodan Zhuang and Xi Zhou and Thomas S. Huang and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2008.4517535},
 grant = {NSF 0414117},
 keywords = {analysis},
 pages = {17-20},
 title = {Feature Analysis and Selection for Acoustic Event Detection},
 year = {2008}
}

@article{zhou000071hmm-based,
 author = {Xi Zhou and Xiaodan Zhuang and Ming Lui and Hao Tang and Mark Hasegawa-Johnson and Thomas Huang},
 doi = {10.1007/978-3-540-68585-2_33},
 grant = {NSF 0414117},
 journal = {Lecture Notes in Computer Science},
 keywords = {analysis},
 pages = {345-353},
 title = {HMM-Based Acoustic Event Detection with AdaBoost Feature Selection},
 volume = {4625},
 year = {2008}
}

@inproceedings{lobdell2008human,
 author = {Bryce Lobdell and Mark Hasegawa-Johnson and Jont B. Allen},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2008-494},
 keywords = {analysis},
 pages = {1797--1800},
 title = {Human Speech Perception and Feature Extraction},
 year = {2008}
}

@inproceedings{mo2008frequency,
 author = {Yoonsook Mo and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {LabPhon 11},
 keywords = {analysis},
 pages = {29-30},
 title = {Frequency and repetition effects outweigh phonetic detail in prominence perception},
 url = {https://labphon.org/sites/default/files/previous_conferences/LabPhon11.pdf#page=51},
 year = {2008}
}

@inproceedings{zhuang2008the,
 author = {Xiaodan Zhuang and Hosung Nam and Mark Hasegawa-Johnson and Louis Goldstein and Elliot Saltzman},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2008-428},
 grant = {NSF 0703624},
 keywords = {analysis},
 pages = {1489--1492},
 title = {The Entropy of Articulatory Phonological Code: Recognizing Gestures from Tract Variables},
 year = {2008}
}

@unpublished{borys2008lovable,
 author = {Sarah Borys},
 keywords = {analysis},
 note = {Cartoons published online},
 title = {Lovable Indestructible Grad Student of Chaos},
 year = {2008}
}

@inproceedings{zhuang2008face,
 author = {Xiaodan Zhuang and Xi Zhou and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {ICPR},
 doi = {10.1109/ICPR.2008.4761364},
 grant = {NSF 0534106},
 keywords = {intelligence},
 pages = {1-4},
 title = {Face Age Estimation Using Patch-based Hidden Markov Model Supervectors},
 year = {2008}
}

@inproceedings{zhou2008a,
 author = {Xi Zhou and Xiaodan Zhuang and Hao Tang and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {ICPR},
 doi = {10.1109/ICPR.2008.4761665},
 grant = {NSF 0534106},
 keywords = {intelligence},
 pages = {1-4},
 title = {A Novel Gaussianized Vector Representation for Natural Scene Categorization},
 year = {2008}
}

@inproceedings{zhou2008sift-bag,
 author = {Xi Zhou and Xiaodan Zhuang and Shuicheng Yan and Shih-Fu Chang and Mark Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {ACM Multimedia},
 doi = {10.1145/1459359.1459391},
 grant = {NSF 0534106},
 keywords = {intelligence},
 pages = {229-238},
 title = {SIFT-Bag Kernel for Video Event Analysis},
 year = {2008}
}

@inproceedings{yan2008regression,
 author = {Shuicheng Yan and Xi Zhou and Ming Liu and Mark Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 doi = {10.1109/CVPR.2008.4587405},
 keywords = {intelligence},
 pages = {1-8},
 title = {Regression from Patch Kernel},
 url = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4587405},
 year = {2008}
}

@inproceedings{huang2008maximum,
 author = {Jui-Ting Huang and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 grant = {NSF 0534133},
 keywords = {recognition},
 title = {Maximum Mutual Information Estimation with Unlabeled Data for Phonetic Classification},
 url = {https://www.isca-archive.org/interspeech_2008/huang08_interspeech.pdf},
 year = {2008}
}

@inproceedings{zhuang000061the,
 author = {Xiaodan Zhuang and Hosung Nam and Mark Hasegawa-Johnson and Louis Goldstein and Elliot Saltzman},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2008-428},
 grant = {NSF 0703624},
 keywords = {recognition},
 pages = {1489--1492},
 title = {The Entropy of Articulatory Phonological Code: Recognizing Gestures from Tract Variables},
 year = {2008}
}

@inproceedings{kantor2008stream,
 author = {Arthur Kantor and Mark Hasegawa-Johnson},
 booktitle = {Proc. ICASSP},
 doi = {10.1109/ICASSP.2008.4518662},
 grant = {NSF 0703624},
 keywords = {recognition},
 pages = {4525-4528},
 title = {Stream Weight Tuning in Dynamic Bayesian Networks},
 year = {2008}
}

@article{hasegawajohnson2008prosodically,
 address = {Taiwan},
 author = {Mark Hasegawa-Johnson and Jennifer Cole and Ken Chen and Partha Lal and Amit Juneja and Taejin Yoon and Sarah Borys and Xiaodan Zhuang},
 grant = {NSF 0414117},
 journal = {Language and Linguistics Monograph Series},
 keywords = {recognition},
 pages = {101-128},
 publisher = {Academica Sinica},
 title = {Prosodically Organized Automatic Speech Recognition},
 volume = {A25},
 year = {2008}
}

@article{yoon2008voice,
 address = {Taiwan},
 author = {Taejin Yoon and Xiaodan Zhuang and Jennifer Cole and Mark Hasegawa-Johnson},
 grant = {NSF 0414117},
 journal = {Language and Linguistics Monograph Series},
 keywords = {recognition},
 pages = {77-100},
 publisher = {Academica Sinica},
 title = {Voice Quality Dependent Speech Recognition},
 volume = {A25},
 year = {2008}
}

@inproceedings{kim2008dysarthric,
 author = {Heejin Kim and Mark Hasegawa-Johnson and Adrienne Perlman and Jon Gunderson and Thomas Huang and Kenneth Watkin and Simone Frame},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2008-480},
 grant = {NIH DC008090A},
 keywords = {recognition},
 pages = {1741-1744},
 title = {Dysarthric Speech Database for Universal Access Research},
 year = {2008}
}

@article{tang2008humanoid,
 author = {Hao Tang and Yun Fu and Jilin Tu and Mark Hasegawa-Johnson and Thomas S. Huang},
 doi = {10.1109/TMM.2008.2001355},
 journal = {IEEE Trans. Multimedia},
 keywords = {synthesis},
 number = {6},
 pages = {969-981},
 title = {Humanoid Audio-Visual Avatar with Emotive Text-to-Speech Synthesis},
 volume = {10},
 year = {2008}
}

@inproceedings{tang2008real-time,
 author = {Hao Tang and Yuxiao Hu and Yun Fu and Mark Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {IEEE International Conference on Multimedia and Expo (ICME)},
 doi = {10.1109/ICME.2008.4607657},
 keywords = {synthesis},
 pages = {1205-1208},
 title = {Real-time conversion from a single 2D face image to a 3D text-driven emotive audio-visual avatar},
 year = {2008}
}

@inproceedings{tang2008two-stage,
 author = {Hao Tang and Xi Zhou and Matthias Odisio and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2008-554},
 grant = {NSF 0426227},
 keywords = {synthesis},
 pages = {2138-2141},
 title = {Two-Stage Prosody Prediction for Emotional Text-to-Speech Synthesis},
 year = {2008}
}

@inproceedings{tang2008eava:,
 author = {Hao Tang and Yun Fu and Jilin Tu and Thomas Huang and Mark Hasegawa-Johnson},
 booktitle = {IEEE Workshop on Applications of Computer Vision (IEEE WACV)},
 doi = {10.1109/WACV.2008.4544003},
 grant = {NSF 0426227},
 keywords = {synthesis},
 pages = {1-6},
 title = {EAVA: A 3D Emotive Audio-Visual Avatar},
 year = {2008}
}

@article{kim2008acoustic,
 author = {Lae-Hoon Kim and Mark Hasegawa-Johnson and Jun-Seok Lim and Koeng-Mo Sung},
 doi = {10.1121/1.2837285},
 journal = {J. Acoust. Soc. Am.},
 keywords = {synthesis},
 number = {4},
 pages = {2043-2053},
 title = {Acoustic model for robustness analysis of optimal multipoint room equalization},
 volume = {123},
 year = {2008}
}

@inproceedings{kim2008optimal,
 author = {Lae-Hoon Kim and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2008.4518674},
 keywords = {synthesis},
 pages = {4573-4576},
 title = {Optimal Speech Estimator Considering Room Response as well as Additive Noise: Different Approaches in Low and High Frequency Range},
 year = {2008}
}

@mastersthesis{borys2008scm,
 author = {Sarah Borys},
 keywords = {recognition},
 school = {University of Illinois},
 title = {An SVM Front End Landmark Speech Recognition System},
 year = {2008}
}

@mastersthesis{li2008incremental,
 author = {Yang Li},
 keywords = {intelligence},
 school = {University of Illinois},
 title = {Incremental Training and Growth of Artificial Neural Networks},
 year = {2008}
}

@inproceedings{yoon000168on,
 address = {Saarbrücken},
 author = {Taejin Yoon and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {Proc. International Congress on Phonetic Sciences (ICPhS)},
 grant = {NSF 0414117},
 keywords = {analysis},
 month = {August},
 pages = {1264:1017-1020},
 title = {On the edge: Acoustic cues to layered prosodic domains},
 url = {http://www.icphs2007.de/conference/Papers/1264/1264.pdf},
 year = {2007}
}

@inproceedings{liu2007frequency,
 address = {Antwerp},
 author = {Ming Liu and Xi Zhou and Mark Hasegawa-Johnson and Thomas S. Huang and Zhengyou Zhang},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2007-120},
 keywords = {recognition},
 month = {August},
 pages = {274-277},
 title = {Frequency Domain Correspondence for Speaker Normalization},
 year = {2007}
}

@inproceedings{hasegawajohnson2007audiovisual,
 address = {Saarbrücken},
 author = {Mark Hasegawa-Johnson and Karen Livescu and Partha Lal and Kate Saenko},
 booktitle = {Proc. International Congress on Phonetic Sciences (ICPhS)},
 grant = {NSF 0121285},
 keywords = {recognition},
 month = {August},
 pages = {1719:297-302},
 title = {Audiovisual Speech Recognition with Articulator Positions as Hidden Variables},
 url = {https://www.researchgate.net/profile/K-Livescu/publication/228926670_Audiovisual_speech_recognition_with_articulator_positions_as_hidden_variables/links/00b7d5201284197994000000/Audiovisual-speech-recognition-with-articulator-positions-as-hidden-variables.pdf},
 year = {2007}
}

@unpublished{hasegawajohnson2007audio-visual,
 author = {Mark Hasegawa-Johnson},
 grant = {NSF 0534106},
 keywords = {recognition},
 month = {June},
 note = {talk given to the Signal Processing Society, IEEE Japan},
 title = {Audio-Visual Speech Recognition: Audio Noise, Video Noise, and Pronunciation Variability},
 year = {2007}
}

@inproceedings{lee000035minimum,
 address = {Istanbul},
 author = {Bowon Lee and Mark Hasegawa-Johnson},
 booktitle = {2007 Biennial on DSP for In-Vehicle and Mobile Systems},
 grant = {Motorola RPS19},
 keywords = {synthesis},
 month = {June},
 title = {Minimum Mean Squared Error A Posteriori Estimation of High Variance Vehicular Noise},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=1d23cdbd3b402db72ed6ea907bdf7f54d3c9dc2e},
 year = {2007}
}

@inproceedings{livescu2007articulatory,
 author = {Karen Livescu and Ozgur Cetin and Mark Hasegawa-Johnson and Simon King and Chris Bartels and Nash Borges and Arthur Kantor and Partha Lal and Lisa Yung and Ari Bezman and Stephen Dawson-Haggerty and Bronwyn Woods and Joe Frankel and Matthew Magimai-Doss and Kate Saenko},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2007.366989},
 keywords = {recognition},
 month = {May},
 pages = {621-624},
 title = {Articulatory Feature-Based Methods for Acoustic and Audio-Visual Speech Recognition: Summary from the 2006 JHU Summer Workshop},
 year = {2007}
}

@inproceedings{yoon2007on,
 address = {Anaheim, CA},
 author = {Taejin Yoon and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {81st Annual Meeting of the Linguistic Society of America},
 grant = {NSF 0414117},
 keywords = {analysis},
 month = {January},
 title = {On the edge: Acoustic cues to layered prosodic domains.},
 url = {http://www.icphs2007.de/conference/Papers/1264/1264.pdf},
 year = {2007}
}

@phdthesis{yoon2007a,
 author = {Taejin Yoon},
 keywords = {analysis},
 school = {University of Illinois},
 title = {A Predictive Model of Prosody Through Grammatical Interface: A Computational Approach},
 url = {https://www.ideals.illinois.edu/items/83925},
 year = {2007}
}

@article{zhang2007extraction,
 author = {Tong Zhang and Mark Hasegawa-Johnson and Stephen E. Levinson},
 doi = {10.1016/j.specom.2005.07.007},
 grant = {NSF 0085980},
 journal = {Speech Communication},
 keywords = {analysis},
 title = {Extraction of Pragmatic and Semantic Salience from Spontaneous Spoken English},
 year = {2007}
}

@inproceedings{zhou2007robust,
 author = {Xi Zhou and Yu Fun and Ming Liu and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {International Conference on Multimedia and Expo},
 doi = {10.1109/ICME.2007.4284618},
 grant = {NSF 0426627},
 keywords = {analysis},
 pages = {188-191},
 title = {Robust Analysis and Weighting on MFCC Components for Speech Recognition and Speaker Identification},
 year = {2007}
}

@inproceedings{liu2007exploring,
 author = {Ming Liu and Zhengyou Zhang and Mark Hasegawa-Johnson and Thomas Huang},
 booktitle = {ICME},
 doi = {10.1109/ICME.2007.4284585},
 grant = {NSF 0426627},
 keywords = {analysis},
 pages = {56-59},
 title = {Exploring Discriminative Learning for Text-Independent Speaker Recognition},
 year = {2007}
}

@article{chang2007brain,
 author = {Soo-Eun Chang and Nicoline Ambrose and Kirk Erickson and Mark Hasegawa-Johnson},
 doi = {10.1016/j.neuroimage.2007.09.067},
 grant = {NIH DC05210},
 journal = {Neuroimage},
 keywords = {analysis},
 title = {Brain Anatomy Differences in Childhood Stuttering},
 year = {2007}
}

@article{cole2007signal-based,
 author = {Jennifer Cole and Yoonsook Mo and Mark Hasegawa-Johnson},
 doi = {10.1515/labphon.2010.022},
 grant = {NSF 0703624)},
 journal = {Journal of Laboratory Phonology},
 keywords = {analysis},
 title = {Signal-based and expectation-based factors in the perception of prosodic prominence},
 year = {2007}
}

@article{cole2007prosodic,
 author = {Jennifer Cole and Heejin Kim and Hansook Choi and Mark Hasegawa-Johnson},
 doi = {10.1016/j.wocn.2006.03.004},
 grant = {NSF 0414117},
 journal = {J Phonetics},
 keywords = {analysis},
 pages = {180-209},
 title = {Prosodic effects on acoustic cues to stop voicing and place of articulation: Evidence from Radio News speech},
 volume = {35},
 year = {2007}
}

@inproceedings{hasegawajohnson2007multi-stream,
 author = {Mark Hasegawa-Johnson},
 booktitle = {IEEE 9th Workshop on Multimedia Signal Processing (MMSP)},
 doi = {10.1109/MMSP.2007.4412884},
 keywords = {recognition},
 pages = {328-331},
 title = {Multi-Stream Approach to Audiovisual Automatic Speech Recognition},
 year = {2007}
}

@inproceedings{fu2007lipreading,
 author = {Yun Fu and Xi Zhou and Ming Liu and Mark Hasegawa-Johnson and Thomas S. Huang},
 booktitle = {IEEE International Conference on Image Processing (ICIP)},
 doi = {10.1109/ICIP.2007.4379312},
 grant = {NSF 0426627},
 keywords = {recognition},
 pages = {III:325-8},
 title = {Lipreading by Locality Discriminant Graph},
 year = {2007}
}

@unpublished{livescu2007articulatory-feature-based,
 author = {Karen Livescu and Özgür Çetin and Mark Hasegawa-Johnson and Simon King and Chris Bartels and Nash Borges and Arthur Kantor and Partha Lal and Lisa Yung and Ari Bezman and Stephen Dawson-Hagerty and Bronwyn Woods and Joe Frankel and Mathew Magimai-Doss and Kate Saenko},
 keywords = {recognition},
 note = {Final report of the WS06 Johns Hopkins Summer Workshop team},
 title = {Articulatory-Feature-Based Methods for Acoustic and Audio-Visual Speech Recognition: 2006 JHU Summer Workshop Final Report.},
 year = {2007}
}

@incollection{chen2007a,
 author = {Ken Chen and Mark Hasegawa-Johnson and Jennifer Cole},
 booktitle = {Robust Speech Recognition and Understanding},
 editor = {Michael Grimm and Kristian Kroschel},
 keywords = {recognition},
 pages = {319-332},
 publisher = {INTECH Publishing},
 title = {A Factored Language Model for Prosody-Dependent Speech Recognition},
 url = {http://www.intechopen.com/books/show/title/robust_speech_recognition_and_understanding},
 year = {2007}
}

@inproceedings{zhu2007cellphone-based,
 author = {Weimo Zhu and Mark Hasegawa-Johnson and Karen Chapman-Novakofski and Arthur Kantor},
 booktitle = {National Nutrient Database Conference},
 keywords = {recognition},
 title = {Cellphone-Based Nutrition E-Diary},
 year = {2007}
}

@inproceedings{zhu2007ecoder,
 author = {Weimo Zhu and Mark Hasegawa-Johnson and Arthur Kantor and Dan Roth and Yong Gao and Youngsik Park and Lin Yang},
 booktitle = {ACSM},
 keywords = {recognition},
 title = {E-coder for Automatic Scoring Physical Activity Diary Data: Development and Validation},
 year = {2007}
}

@unpublished{hasegawajohnson2006phonology,
 author = {Mark Hasegawa-Johnson},
 grant = {NSF 0414117},
 keywords = {recognition},
 month = {November},
 note = {Director's Seminar Series, Beckman Institute, University of Illinois at Urbana-Champaign},
 title = {Phonology and the Art of Automatic Speech Recognition},
 year = {2006}
}

@inproceedings{chitturi2006time,
 author = {Rahul Chitturi and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2006-105},
 keywords = {analysis},
 month = {September},
 pages = {paper 1904-Thu1CaP.14},
 title = {Novel Time-Domain Multi-class SVMs for Landmark Detection},
 year = {2006}
}

@unpublished{hasegawajohnson2006object,
 author = {Mark Hasegawa-Johnson},
 grant = {NSF 0534106},
 keywords = {recognition},
 month = {August},
 note = {talk given to the Artificial Intelligence, Vision, and Robotics seminar series},
 title = {Object Tracking and Asynchrony in Audio-Visual Speech Recognition.},
 year = {2006}
}

@inproceedings{hasegawajohnson2006dealing,
 author = {Mark Hasegawa-Johnson},
 booktitle = {tutorial presentation given at WS06, Center for Language and Speech Processing},
 grant = {NSF 0121285},
 keywords = {recognition},
 month = {July},
 title = {Dealing with Acoustic Noise. Part IIII: Video},
 year = {2006}
}

@unpublished{hasegawajohnson2006dealing1,
 author = {Mark Hasegawa-Johnson},
 booktitle = {Tutorial presentation given at WS06, Center for Language and Speech Processing},
 keywords = {synthesis},
 month = {July},
 title = {Dealing with Acoustic Noise. Part II: Beamforming.},
 year = {2006}
}

@unpublished{hasegawajohnson2006dealing2,
 author = {Mark Hasegawa-Johnson},
 booktitle = {Tutorial presentation given at WS06, Center for Language and Speech Processing},
 keywords = {synthesis},
 month = {July},
 title = {Dealing with Acoustic Noise. Part I: Spectral Estimation.},
 year = {2006}
}

@inproceedings{hasegawajohnson2006hmm-based,
 author = {Mark Hasegawa-Johnson and Jonathan Gunderson and Adrienne Perlman and Thomas Huang},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2006.1660840},
 grant = {NSF 0534106},
 keywords = {recognition},
 month = {May},
 pages = {III:1060-3},
 title = {HMM-Based and SVM-Based Recognition of the Speech of Talkers with Spastic Dysarthria},
 year = {2006}
}

@inproceedings{kim2006generalized,
 author = {Lae-Hoon Kim and Mark Hasegawa-Johnson and Keung-Mo Sung},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2006.1660591},
 keywords = {synthesis},
 month = {May},
 pages = {III:65-8},
 title = {Generalized Optimal Multi-Microphone Speech Enhancement Using Sequential Minimum Variance Distortionless Response (MVDR) Beamforming and Postfiltering},
 year = {2006}
}

@article{zhang2006cognitive,
 author = {Tong Zhang and Mark Hasegawa-Johnson and Stephen E. Levinson},
 doi = {10.1016/j.specom.2005.09.006},
 grant = {NSF 0085980},
 journal = {Speech Communication},
 keywords = {analysis},
 number = {6},
 page = {616-632},
 title = {Cognitive State Classification in a spoken tutorial dialogue system},
 volume = {48},
 year = {2006}
}

@inproceedings{reddy2006mclc,
 author = {Rajiv Reddy and Mark Hasegawa-Johnson},
 booktitle = {Midwest Computational Linguistics Colloquium},
 keywords = {analysis},
 title = {Analysis of Pitch Contours in Repetition-Disfluency using Stem-ML},
 url = {https://www.researchgate.net/profile/Rajiv-Reddy-7/publication/228967280_Analysis_of_Pitch_Contours_in_Repetition-Disfluency_using_Stem-ML/links/00b49536b0b12a63e2000000/Analysis-of-Pitch-Contours-in-Repetition-Disfluency-using-Stem-ML.pdf},
 year = {2006}
}

@inproceedings{chang2006deficient,
 address = {Atlanta, GA},
 author = {Soo-Eun Chang and Kirk I. Erickson and Nicoline G. Ambrose and Mark Hasegawa-Johnson and C.L. Ludlow},
 booktitle = {Society for Neuroscience},
 grant = {NIH DC05210},
 keywords = {analysis},
 title = {Deficient white matter development in left hemisphere speech-language regions in children who stutter},
 year = {2006}
}

@inproceedings{chitturi2006entropy,
 author = {Rahul Chitturi and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech 2006},
 doi = {10.21437/Interspeech.2006-468},
 pages = {paper 1911-Wed1FoP.8},
 title = {Novel entropy based moving average refiners for HMM landmarks},
 year = {2006}
}

@inproceedings{kim2006acoustic,
 address = {Dresden},
 author = {Heejin Kim and Taejin Yoon and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {Proceedings of Speech Prosody},
 grant = {NSF 0414117},
 keywords = {analysis},
 title = {Acoustic differentiation of L- and L-L% in Switchboard and Radio News speech},
 url = {https://www.isca-speech.org/archive/speechprosody_2006/kim06d_speechprosody.html},
 year = {2006}
}

@unpublished{reddy2006thesis,
 author = {Rajiv Reddy},
 howpublished = {B.S. Thesis, University of Illinois},
 keywords = {analysis},
 title = {Analysis of Pitch Contours in Repetition-Disfluency Using Stem-ML},
 year = {2006}
}

@phdthesis{lee2006robust,
 author = {Bowon Lee},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Robust Speech Recognition in a Car Using a Microphone Array},
 url = {https://www.ideals.illinois.edu/items/82279},
 year = {2006}
}

@unpublished{goudeseune2006avicar,
 author = {Camille Goudeseune and Bowon Lee},
 booktitle = {Promotional Film},
 grant = {Motorola RPS19},
 keywords = {recognition},
 title = {AVICAR: Audio-Visual Speech Recognition in a Car Environment},
 year = {2006}
}

@article{chen2006prosody,
 author = {Ken Chen and Mark Hasegawa-Johnson and Aaron Cohen and Sarah Borys and Sung-Suk Kim and Jennifer Cole and Jeung-Yoon Choi},
 doi = {10.1109/TSA.2005.853208},
 grant = {NSF 0132900},
 journal = {IEEE Transactions on Speech and Audio Processing},
 keywords = {recognition},
 number = {1},
 pages = {232-245},
 title = {Prosody Dependent Speech Recognition on Radio News Corpus of American English},
 volume = {14},
 year = {2006}
}

@inproceedings{borys2005distinctive,
 author = {Sarah Borys and Mark Hasegawa-Johnson},
 booktitle = {ISCA Interspeech},
 doi = {10.21437/Interspeech.2005-200},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {October},
 title = {Distinctive Feature Based SVM Discriminant Features for Improvements to Phone Recognition on Telephone Band Speech},
 year = {2005}
}

@inproceedings{kim2005generalized,
 address = {New York},
 author = {Lae-Hoon Kim and Mark Hasegawa-Johnson},
 booktitle = {119th Convention of the Audio Engineering Society},
 keywords = {synthesis},
 month = {October},
 title = {Generalized multi-microphone spectral amplitude estimation based on correlated noise model},
 year = {2005}
}

@inproceedings{hasegawajohnson2004landmark,
 author = {Mark Hasegawa-Johnson and James Baker and Sarah Borys and Ken Chen and Emily Coogan and Steven Greenberg and Amit Juneja and Katrin Kirchhoff and Karen Livescu and Srividya Mohan and Jennifer Muller and Kemal Sönmez and Tianyu Wang},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2005.1415088},
 grant = {NSF 0121285},
 keywords = {recognition},
 month = {March},
 pages = {1213-1216},
 title = {Landmark-Based Speech Recognition: Report of the 2004 Johns Hopkins Summer Workshop},
 year = {2005}
}

@inproceedings{zhu2005accuracy,
 author = {Weimo Zhu and Mark Hasegawa-Johnson and Mital Arun Gandhi},
 booktitle = {Association of Test Publishers (ATP): Innovations in Testing},
 keywords = {recognition},
 month = {March},
 title = {Accuracy of Voice-Recognition Technology in Collecting Behavior Diary Data},
 year = {2005}
}

@article{yoon2005acoustic,
 author = {Tae-Jin Yoon and Cole and Jennifer and Mark Hasegawa-Johnson and Chilin Shih},
 doi = {10.1121/1.4778287},
 grant = {NSF 0414117},
 journal = {The Journal of the Acoustical Society of America},
 keywords = {analysis},
 number = {4},
 pages = {2621},
 title = {Acoustic correlates of non-modal phonation in telephone speech},
 volume = {117},
 year = {2005}
}

@unpublished{yoon2005mapping,
 address = {Columbus, OH},
 author = {Taejin Yoon},
 grant = {NSF 0414117},
 keywords = {analysis},
 note = {Presentation at the Midwest Computational Linguistics Colloquium},
 title = {Mapping Syntax and Prosody},
 year = {2005}
}

@article{choi2005finding,
 author = {Jeung-Yoon Choi and Mark Hasegawa-Johnson and Jennifer Cole},
 doi = {10.1121/1.2010288},
 journal = {Journal of the Acoustical Society of America},
 keywords = {analysis},
 number = {4},
 pages = {2579-88},
 title = {Finding Intonational Boundaries Using Acoustic Cues Related to the Voice Source},
 volume = {118},
 year = {2005}
}

@inproceedings{cole2005prosodic,
 address = {Aix-en-Provence, France},
 author = {Jennifer Cole and Mark Hasegawa-Johnson and Chilin Shih and Eun-Kyung Lee and Heejin Kim and H. Lu and Yoonsook Mo and Tae-Jin Yoon},
 booktitle = {Disfluency In Spontaneous Speech (DISS'05)},
 grat = {NSF 0414117},
 keywords = {analysis},
 pages = {53-58},
 title = {Prosodic Parallelism as a Cue to Repetition and Hesitation Disfluency},
 url = {https://www.isca-speech.org/archive/diss_2005/cole05_diss.html},
 year = {2005}
}

@inproceedings{kim2005phonetic,
 address = {Columbus, OH},
 author = {Yeojin Kim and Mark Hasegawa-Johnson},
 booktitle = {Midwest Computational Linguistics Colloquium},
 grant = {NSF 0132900},
 keywords = {recognition},
 title = {Phonetic Segment Rescoring Using SVMs},
 year = {2005}
}

@unpublished{hasegawajohnson2005landmark-based,
 author = {Mark Hasegawa-Johnson and James Baker and Steven Greenberg and Katrin Kirchhoff and Jennifer Muller and Kemal Sonmez and Sarah Borys and Ken Chen and Amit Juneja and Katrin Kirchhoff and Karen Livescu and Srividya Mohan and Emily Coogan and Tianyu Wang},
 keywords = {recognition},
 note = {Final report of the WS04 Johns Hopkins Summer Workshop team},
 number = {WS04},
 title = {Landmark-Based Speech Recognition: Report of the 2004 Johns Hopkins Summer Workshop},
 year = {2005}
}

@phdthesis{zheng2005feature,
 author = {Yanli Zheng},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Acoustic Modeling and Feature Extraction for Speech Recognition},
 url = {https://www.ideals.illinois.edu/items/82196},
 year = {2005}
}

@article{hasegawajohnson2005simultaneous,
 author = {Mark Hasegawa-Johnson and Ken Chen and Jennifer Cole and Sarah Borys and Sung-Suk Kim and Aaron Cohen and Tong Zhang and Jeung-Yoon Choi and Heejin Kim and Taejin Yoon and Sandra Chavarria},
 doi = {10.1016/j.specom.2005.01.009},
 grant = {NSF 0132900},
 journal = {Speech Communication},
 keywords = {recognition},
 number = {3-4},
 pages = {418-439},
 title = {Simultaneous Recognition of Words and Prosody in the Boston University Radio Speech Corpus},
 volume = {46},
 year = {2005}
}

@inproceedings{zhang2005a,
 author = {Tong Zhang and Mark Hasegawa-Johnson and Stephen E. Levinson},
 booktitle = {Proceedings of the National Conference on Artificial Intelligence},
 grant = {NSF 0085980},
 keywords = {recognition},
 pages = {10.1.1.80.879:1-8},
 title = {A Hybrid Model for Spontaneous Speech Understanding},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=8110962ce5089070665624355945933b54b7e8eb},
 year = {2005}
}

@inproceedings{kantor2005restricted,
 author = {Arthur Kantor and Weimo Zhu and Mark Hasegawa-Johnson},
 booktitle = {Midwest Computational Linguistics Colloquium},
 keywords = {recognition},
 title = {Restricted domain speech classification using automatic transcription and SVMs},
 year = {2005}
}

@mastersthesis{co2005room,
 author = {Christopher Co},
 keywords = {analysis},
 school = {University of Illinois},
 software = {http://isle.illinois.edu/speech_web_lg/software/2013/co2013software.tgz},
 title = {Room Reconstruction and Navigation Using Acoustically Obtained Room Impulse Responses and a Mobile Robot Platform},
 url = {https://www.ideals.illinois.edu/items/42150},
 year = {2005}
}

@inproceedings{chang2004an,
 author = {Soo-Eun Chang and Nicoline Ambrose and Mark Hasegawa-Johnson},
 booktitle = {ASHA Convention},
 keywords = {analysis},
 month = {November},
 title = {An MRI (DTI) study on children with persistent developmental stuttering},
 year = {2004}
}

@inproceedings{borys000029modeling,
 author = {Sarah Borys and Mark Hasegawa-Johnson and Ken Chen and Aaron Cohen},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-756},
 grant = {NSF 0132900},
 keywords = {analysis},
 month = {October},
 pages = {3013--3016},
 title = {Modeling and Recognition of Phonetic and Prosodic Factors for Improvements to Acoustic Speech Recognition Models},
 year = {2004}
}

@inproceedings{zhang2004children,
 author = {Mark Hasegawa-Johnson and Stephen E. Levinson and Tong Zhang},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-552},
 grant = {NSF 0085980},
 keywords = {analysis},
 month = {October},
 pages = {1441--1444},
 title = {Children's Emotion Recognition in an Intelligent Tutoring Scenario},
 year = {2004}
}

@inproceedings{zheng2004stop,
 author = {Yanli Zheng and Mark Hasegawa-Johnson and Sarah Borys},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-403},
 grant = {NSF 0132900},
 keywords = {analysis},
 month = {October},
 pages = {396-399},
 title = {Stop Consonant Classification by Dynamic Formant Trajectory},
 year = {2004}
}

@inproceedings{yoon2004intertranscriber,
 author = {Tae-Jin Yoon and Sandra Chavarria and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-659},
 keywords = {analysis},
 month = {October},
 pages = {2729--2732},
 title = {Intertranscriber Reliability of Prosodic Labeling on Telephone Conversation Using ToBI},
 year = {2004}
}

@unpublished{hasegawajohnson2004landmark-based,
 author = {Mark Hasegawa-Johnson},
 booktitle = {talk given at Tsinghua University},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {October},
 title = {Landmark-Based Speech Recognition: The Marriage of High-Dimensional Machine Learning Techniques with Modern Linguistic Representations},
 year = {2004}
}

@inproceedings{hasegawajohnson2004factorial,
 author = {Mark Hasegawa-Johnson and Ameya Deoras},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-637},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {October},
 pages = {2093--2096},
 title = {A Factorial HMM Approach to Robust Isolated Digit Recognition in Background Music.},
 year = {2004}
}

@inproceedings{chen2004modeling,
 author = {Ken Chen and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-557},
 grant = {NSF 0414117},
 keywords = {recognition},
 month = {October},
 pages = {400-403},
 title = {Modeling pronunciation variation using artificial neural networks for English spontaneous speech},
 year = {2004}
}

@inproceedings{lee2004avicar,
 author = {Bowon Lee and Mark Hasegawa-Johnson and Camille Goudeseune and Suketu Kamdar and Sarah Borys and Ming Liu and Thomas Huang},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-424},
 grant = {Motorola RPS19},
 keywords = {recognition},
 month = {October},
 pages = {380-383},
 title = {AVICAR: Audio-Visual Speech Corpus in a Car Environment.},
 year = {2004}
}

@inproceedings{borys2004modeling,
 author = {Sarah Borys and Mark Hasegawa-Johnson and Ken Chen and Aaron Cohen},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-756},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {October},
 pages = {3013--3016},
 title = {Modeling and Recognition of Phonetic and Prosodic Factors for Improvements to Acoustic Speech Recognition Models},
 year = {2004}
}

@unpublished{hasegawajohnson2004tsinghua,
 author = {Mark Hasegawa-Johnson},
 booktitle = {talk given at Tsinghua University},
 grant = {NSF 0414117},
 keywords = {recognition},
 month = {October},
 title = {Speech Recognition Models of the Interdependence Among Syntax, Prosody, and Segmental Acoustics},
 year = {2004}
}

@inproceedings{gandhi2004source,
 author = {Mital Gandhi and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Interspeech.2004-710},
 keywords = {synthesis},
 month = {October},
 pages = {2673--2676},
 title = {Source Separation using Particle Filters},
 year = {2004}
}

@inproceedings{hasegawajohnson2004experiments,
 author = {Mark Hasegawa-Johnson and Sarah Borys and Ken Chen},
 booktitle = {Sound to Sense: Workshop in Honor of Kenneth N. Stevens},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {June},
 title = {Experiments in Landmark-Based Speech Recognition},
 year = {2004}
}

@inproceedings{hasegawajohnson2004hlt,
 author = {Mark Hasegawa-Johnson and Jennifer Cole and Chilin Shih and Ken Chen and Aaron Cohen and Sandra Chavarria and Heejin Kim and Taejin Yoon and Sarah Borys and Jeung-Yoon Choi},
 booktitle = {HLT/NAACL Workshop on Higher-Level Knowledge in Automatic Speech Recognition and Understanding},
 grant = {NSF 0414117},
 keywords = {recognition},
 month = {May},
 pages = {56-63},
 title = {Speech Recognition Models of the Interdependence Among Syntax, Prosody, and Segmental Acoustics},
 url = {https://aclanthology.org/W04-3010/},
 year = {2004}
}

@inproceedings{chen2004maximum,
 address = {Nara, Japan},
 author = {Ken Chen and Mark Hasegawa-Johnson and Aaron Cohen and Jennifer Cole},
 booktitle = {SpeechProsody},
 grant = {NSF 0132900},
 keywords = {analysis},
 month = {March},
 pages = {509-512},
 title = {A Maximum Likelihood Prosody Recognizer},
 url = {https://www.isca-speech.org/archive/speechprosody_2004/chen04b_speechprosody.html},
 year = {2004}
}

@inproceedings{ren2004speaker,
 address = {Nara, Japan},
 author = {Yuexi Ren and Sung-Suk Kim and Mark Hasegawa-Johnson and Jennifer Cole},
 booktitle = {Proc. Speech Prosody 2004},
 grant = {NSF 0085980},
 keywords = {analysis},
 month = {March},
 pages = {521--524},
 title = {Speaker-Independent Automatic Detection of Pitch Accent},
 url = {https://www.isca-speech.org/archive/speechprosody_2004/ren04_speechprosody.html},
 year = {2004}
}

@inproceedings{kim2004the,
 address = {Nara, Japan},
 author = {Heejin Kim and Jennifer Cole and Hansook Choi and Mark Hasegawa-Johnson},
 booktitle = {SpeechProsody},
 keywords = {analysis},
 month = {March},
 pages = {29-32},
 title = {The Effect of Accent on Acoustic Cues to Stop Voicing and Place of Articulation in Radio News Speech},
 url = {https://www.isca-speech.org/archive/speechprosody_2004/kim04_speechprosody.html},
 year = {2004}
}

@inproceedings{chavarria000179acoustic,
 address = {Nara, Japan},
 author = {Sandra Chavarria and Taejin Yoon and Jennifer Cole and Mark Hasegawa-Johnson},
 booktitle = {Speech Prosody},
 keywords = {analysis},
 month = {March},
 pages = {333-336},
 title = {Acoustic differentiation of ip and IP boundary levels: Comparison of L- and L-L% in the Switchboard corpus},
 url = {https://www.isca-speech.org/archive/speechprosody_2004/chavarria04_speechprosody.html},
 year = {2004}
}

@inproceedings{chen2004how,
 address = {Nara, Japan},
 author = {Ken Chen and Mark Hasegawa-Johnson},
 booktitle = {Speech Prosody},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {March},
 pages = {583-586},
 title = {How Prosody Improves Word Recognition},
 url = {https://www.isca-speech.org/archive/speechprosody_2004/chen04c_speechprosody.html},
 year = {2004}
}

@inproceedings{hasegawajohnson04automatic,
 author = {Mark Hasegawa-Johnson and Stephen Levinson and Tong Zhang},
 booktitle = {Proc. Interspeech 2004},
 doi = {10.21437/Interspeech.2004-223},
 keywords = {analysis},
 pages = {581--584},
 title = {Automatic detection of contrast for speech understanding},
 year = {2004}
}

@inproceedings{hasegawajohnson2004automatic,
 author = {Mark Hasegawa-Johnson and Stephen Levinson and Tong Zhang},
 booktitle = {Proc. Interspeech 2004},
 doi = {10.21437/Interspeech.2004-223},
 grant = {NSF 0085980},
 pages = {581--584},
 title = {Automatic detection of contrast for speech understanding},
 year = {2004}
}

@inproceedings{chen2004an,
 author = {Ken Chen and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2004.1326034},
 grant = {NSF 0132900},
 keywords = {analysis},
 title = {An Automatic Prosody Labeling System Using ANN-Based Syntactic-Prosodic Model and GMM-Based Acoustic-Prosodic Model},
 year = {2004}
}

@article{kim2004automatic,
 author = {Sung-Suk Kim and Mark Hasegawa-Johnson and Ken Chen},
 doi = {10.1109/LSP.2004.830114},
 grant = {NSF 0132900},
 journal = {IEEE Signal Processing Letters},
 keywords = {analysis},
 number = {7},
 pages = {645-648},
 title = {Automatic Recognition of Pitch Movements Using Multilayer Perceptron and Time-Delay Recursive Neural Network},
 volume = {11},
 year = {2004}
}

@inproceedings{zheng2004formant,
 author = {Yanli Zheng and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2004.1326048},
 grant = {NSF 0132900},
 keywords = {analysis},
 title = {Formant Tracking by Mixture State Particle Filter},
 year = {2004}
}

@inproceedings{yoon2004local,
 address = {University of Illinois at Urbana-Champaign},
 author = {Tae-Jin Yoon and Heejin Kim and Sandra Chavarría.},
 booktitle = {Labphon 9},
 keywords = {analysis},
 title = {Local Acoustic Cues Distinguishing Two Levels of prosodic Phrasing: Speech Corpus Evidence},
 url = {https://www.researchgate.net/profile/Tae-Jin-Yoon/publication/238592404_Local_Acoustic_Cues_Distinguish_Two_Levels_of_Prosodic_Phrasing_Speech_Corpus_Evidence/links/5575664408ae753637500253/Local-Acoustic-Cues-Distinguish-Two-Levels-of-Prosodic-Phrasing-Speech-Corpus-Evidence.pdf},
 year = {2004}
}

@article{omar2004model,
 author = {Mohammad Kamal Omar and Mark Hasegawa-Johnson},
 doi = {10.1109/TSP.2004.834344},
 grant = {NSF 0132900},
 journal = {IEEE Transactions on Signal Processing},
 keywords = {intelligence},
 number = {10},
 pages = {2701-2710},
 title = {Model Enforcement: A Unified Feature Transformation Framework for Classification and Recognition},
 volume = {52},
 year = {2004}
}

@inproceedings{deoras2004icassp,
 author = {Ameya Deoras and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2004.1326122},
 grant = {NSF 0132900},
 keywords = {recognition},
 title = {A Factorial HMM Approach to Simultaneous Recognition of Isolated Digits Spoken by Multiple Talkers on One Audio Channel},
 year = {2004}
}

@unpublished{geirhofer2004feature,
 author = {Stefan Geirhofer},
 keywords = {recognition},
 note = {Undergraduate research project},
 title = {Feature Reduction with Linear Discriminant Analysis and its Performance on Phoneme Recognition},
 year = {2004}
}

@inproceedings{ren2004semantic,
 address = {Madeira, Portugal},
 author = {Yuexi Ren and Mark Hasegawa-Johnson and Stephen E. Levinson},
 booktitle = {Intl. Conf. on Intelligent User Interfaces},
 grant = {NSF 0085980},
 keywords = {recognition},
 title = {Semantic analysis for a speech user interface in an intelligent-tutoring system},
 url = {http://portal.acm.org/citation.cfm?doid=964442.964516},
 year = {2004}
}

@phdthesis{chen2004prosody,
 author = {Ken Chen},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Prosody Dependent Speech Recognition on American Radio News Speech},
 url = {https://www.ideals.illinois.edu/items/82155},
 year = {2004}
}

@mastersthesis{cohen2004survey,
 author = {Aaron Cohen},
 keywords = {analysis},
 school = {University of Illinois},
 title = {A Survey of Machine Learning Methods for Predicting Prosody in Radio Speech},
 year = {2004}
}

@inproceedings{zheng2003particle,
 author = {Yanli Zheng and Mark Hasegawa-Johnson},
 booktitle = {IEEE Workshop on Statistical Signal Processing},
 doi = {10.1109/SSP.2003.1289549},
 grant = {NSF 0132900},
 keywords = {analysis},
 month = {September},
 pages = {581-584},
 title = {Particle Filtering Approach to Bayesian Formant Tracking},
 year = {2003}
}

@inproceedings{omar2003maximum,
 author = {Mohammed Kamal Omar and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Eurospeech.2003-181},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {September},
 pages = {505-508},
 title = {Maximum Conditional Mutual Information Projection For Speech Recognition},
 year = {2003}
}

@inproceedings{omar2003interspeech,
 author = {Mohammed Kamal Omar and Mark Hasegawa-Johnson},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Eurospeech.2003-685},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {September},
 pages = {2497-2500},
 title = {Non-Linear Maximum Likelihood Feature Transformation For Speech Recognition},
 year = {2003}
}

@inproceedings{chen2003prosody,
 author = {Ken Chen and Mark Hasegawa-Johnson and Aaron Cohen and Sarah Borys and Jennifer Cole},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/Eurospeech.2003-153},
 keywords = {recognition},
 month = {September},
 pages = {393-396},
 software = {http://isle.illinois.edu/speech_web_lg/software/2003/Durhmm3.0.zip},
 title = {Prosody Dependent Speech Recognition with Explicit Duration Modelling at Intonational Phrase Boundaries},
 year = {2003}
}

@inproceedings{zhang000013mental,
 author = {Tong Zhang and Mark Hasegawa-Johnson and Stephen E. Levinson},
 booktitle = {ISCA/IEEE Workshop on Spontaneous Speech Processing and Recognition (SSPR)},
 grant = {NSF 0085980},
 keywords = {analysis},
 month = {April},
 pages = {MAP17.1-4},
 title = {Mental State Detection of Dialogue System Users via Spoken Language},
 url = {https://www.isca-speech.org/archive/sspr_2003/zhang03_sspr.html},
 year = {2003}
}

@inproceedings{zheng2003acoustic,
 author = {Yanli Zheng and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2003.1198890},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {April},
 pages = {I:752-755},
 title = {Acoustic segmentation using switching state Kalman Filter},
 year = {2003}
}

@article{zheng2003parafac,
 author = {Yanli Zheng and Mark Hasegawa-Johnson and Shamala Pizza},
 doi = {10.1121/1.1520538},
 grant = {NIH DC0032301},
 journal = {Journal of the Acoustical Society of America},
 keywords = {analysis},
 month = {January},
 number = {1},
 pages = {478-486},
 title = {Analysis of the three-dimensional tongue shape using a three-index factor analysis model},
 volume = {113},
 year = {2003}
}

@inproceedings{zhang2003an,
 author = {Tong Zhang and Mark Hasegawa-Johnson and Stephen E. Levinson},
 booktitle = {Australian conference on computer-human interactionq (OZCHI)},
 grant = {NSF 0085980},
 keywords = {analysis},
 pages = {498-501},
 title = {An empathic-tutoring system using spoken language},
 url = {https://www.researchgate.net/profile/Stephen-Levinson-2/publication/228805591_An_Empathic-tutoring_System_Using_Spoken_Language/links/54d389ac0cf2b0c6146dabde/An-Empathic-tutoring-System-Using-Spoken-Language.pdf},
 year = {2003}
}

@inproceedings{chen2003an,
 author = {Ken Chen and Mark Hasegawa-Johnson and Sung-Suk Kim},
 booktitle = {International Conference on Systems, Cybernetics, and Intelligence},
 keywords = {analysis},
 title = {An Intonational Phrase Boundary and Pitch Accent Dependent Speech Recognizer},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=e9e5670e89cc257c290bc5787bb0c46ffc6061fa},
 year = {2003}
}

@inproceedings{chen2003improving,
 author = {Ken Chen and Mark Hasegawa-Johnson},
 booktitle = {ASRU},
 doi = {10.1109/ASRU.2003.1318480},
 keywords = {analysis},
 title = {Improving the robustness of prosody dependent language modeling based on prosody syntax cross-correlation},
 year = {2003}
}

@article{hasegawa-johnson2003vowel,
 author = {Mark Hasegawa-Johnson and Shamala Pizza and Abeer Alwan and Jul Cha and Katherine Haker},
 doi = {10.1044/1092-4388(2003/059)},
 grant = {NIH DC0032301},
 journal = {Journal of Speech, Language, and Hearing Research},
 keywords = {analysis},
 number = {3},
 pages = {738-753},
 title = {Vowel Category Dependence of the Relationship Between Palate Height, Tongue Height, and Oral Area},
 volume = {46},
 year = {2003}
}

@inproceedings{hasegawa-johnson2003bayesian,
 address = {St. Louis, MO},
 author = {Mark Hasegawa-Johnson},
 booktitle = {IEEE Workshop on Statistical Signal Processing},
 doi = {10.1109/SSP.2003.1289432},
 grant = {NSF 0132900},
 keywords = {analysis},
 pages = {393-396},
 title = {Bayesian Learning for Models of Human Speech Perception},
 year = {2003}
}

@inproceedings{cole000180the,
 author = {Jennifer Cole and Hansook Choi and Heejin Kim and Mark Hasegawa-Johnson},
 booktitle = {ICPhS},
 keywords = {analysis},
 pages = {2665-2668},
 title = {The effect of accent on the acoustic cues to stop voicing in Radio News speech},
 url = {https://www.internationalphoneticassociation.org/icphs-proceedings/ICPhS2003/papers/p15_2665.pdf},
 year = {2003}
}

@inproceedings{omar2003non-linear,
 author = {Mohamed Kamal Omar and Mark Hasegawa-Johnson},
 booktitle = {Proc. 8th European Conference on Speech Communication and Technology (Eurospeech 2003)},
 doi = {10.21437/Eurospeech.2003-685},
 pages = {2497--2500},
 title = {Non-linear maximum likelihood feature transformation for speech recognition},
 year = {2003}
}

@unpublished{deoras2003a,
 author = {Ameya Deoras},
 keywords = {recognition},
 note = {B.S. Thesis, University of Illinois},
 title = {A Factorial HMM Approach to Robust Isolated Digit Recognition in Non-Stationary Noise.},
 year = {2003}
}

@phdthesis{omar2003acoustic,
 author = {Mohamed Kamal Mahmoud Omar},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Acoustic Feature Design for Speech Recognition: A Statistical Information-Theoretic Approach},
 url = {https://www.ideals.illinois.edu/items/82130},
 year = {2003}
}

@article{omar2003approximately,
 author = {Mohammed Kamal Omar and Mark Hasegawa-Johnson},
 doi = {10.1109/TSA.2003.814457},
 grant = {NSF 0132900},
 journal = {IEEE Transactions on Speech and Audio Processing},
 keywords = {recognition},
 number = {6},
 pages = {660-671},
 title = {Approximately Independent Factors of Speech Using Nonlinear Symplectic Transformation},
 volume = {11},
 year = {2003}
}

@inproceedings{omar2003ccct,
 author = {Mohammed Kamal Omar and Mark Hasegawa-Johnson},
 booktitle = {International Conference on Computer, Communication and Control Technologies (CCCT '03)},
 grant = {NSF 0132900},
 keywords = {recognition},
 title = {Non-Linear Independent Component Analysis for Speech Recognition},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=d95f5f7198a3463efa9490533550de5ec02234e2},
 year = {2003}
}

@inproceedings{omar2003strong-sense,
 address = {St. Louis, MO},
 author = {Mohammed Kamal Omar and Mark Hasegawa-Johnson},
 booktitle = {IEEE Workshop on Statistical Signal Processing},
 doi = {10.1109/SSP.2003.1289454},
 grant = {NSF 0132900},
 keywords = {recognition},
 pages = {473-476},
 title = {Strong-Sense Class-Dependent Features for Statistical Recognition},
 year = {2003}
}

@inproceedings{chen2003wssp,
 address = {St. Louis, MO},
 author = {Ken Chen and Mark Hasegawa-Johnson and Jennifer Cole},
 booktitle = {IEEE Workshop on Statistical Signal Processing},
 doi = {10.1109/TSA.2005.853208},
 keywords = {recognition},
 title = {Prosody Dependent Speech Recognition on Radio News},
 year = {2003}
}

@unpublished{borys2003recognition,
 author = {Sarah Borys},
 keywords = {recognition},
 note = {B.S. Thesis, University of Illinois},
 title = {Recognition of Prosodic Factors and Detection of Landmarks for Improvements to Continuous Speech Recognition Systems},
 year = {2003}
}

@inproceedings{borys2003the,
 author = {Sarah Borys and Mark Hasegawa-Johnson and Jennifer Cole},
 booktitle = {ACL Student Session},
 grant = {NSF 0132900},
 keywords = {recognition},
 title = {The Importance of Prosodic Factors in Phoneme Modeling with Applications to Speech Recognition},
 year = {2003}
}

@article{borys2003prosody,
 author = {Sarah Borys and Mark Hasegawa-Johnson and Jennifer Cole},
 journal = {Illinois Journal of Undergraduate Research},
 keywords = {recognition},
 title = {Prosody as a Conditioning Variable in Speech Recognition},
 url = {https://www.researchgate.net/profile/Jennifer-Cole-6/publication/2842059_Prosody_As_A_Conditioning_Variable_In_Speech_Recognition/links/0912f50aa6042dd0bd000000/Prosody-As-A-Conditioning-Variable-In-Speech-Recognition.pdf},
 year = {2003}
}

@article{lee2003open,
 author = {Bowon Lee and Mark Hasegawa-Johnson and Camille Goudeseune},
 doi = {10.1121/1.4780198},
 journal = {J. Acoust. Soc. Am.},
 keywords = {synthesis},
 number = {4},
 pages = {2202-2203},
 title = {Open Loop Multichannel Inversion of Room Impulse Response},
 volume = {113},
 year = {2003}
}

@incollection{hasegawajohnson2002speech,
 address = {NY},
 author = {Mark Hasegawa-Johnson and Abeer Alwan},
 booktitle = {Wiley Encyclopedia of Telecommunications and Signal Processing},
 editor = {J. Proakis},
 grant = {NSF 0132900},
 keywords = {synthesis},
 month = {December},
 publisher = {Wiley and Sons},
 title = {Speech Coding: Fundamentals and Applications},
 year = {2002}
}

@inproceedings{omar2002evaluation,
 address = {Denver, CO},
 author = {Mohammed Kamal Omar and Ken Chen and Mark Hasegawa-Johnson and Yigal Brandman},
 booktitle = {Proc. Interspeech},
 doi = {10.21437/ICSLP.2002-582},
 keywords = {recognition},
 month = {September},
 pages = {2129-2132},
 title = {An Evaluation of using Mutual Information for Selection of Acoustic-Features Representation of Phonemes for Speech Recognition},
 year = {2002}
}

@inproceedings{levinson2002multimodal,
 author = {Stephen E. Levinson and Thomas S. Huang and Mark A. Hasegawa-Johnson and Ken Chen and Stephen Chu and Ashutosh Garg and Zhinian Jing and Danfeng Li and J. Lin and Mohammed Kamal Omar and Z. Wen},
 booktitle = {ARPA Workshop on Multimodal Speech Recognition and SPINE},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {June},
 title = {Multimodal Dialog Systems Research at Illinois},
 url = {https://apps.dtic.mil/sti/pdfs/ADA415344.pdf#page=39},
 year = {2002}
}

@inproceedings{jing2002auditory-modeling,
 author = {Zhinian Jing and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2002.5745632},
 grant = {NSF 0132900},
 keywords = {recognition},
 month = {May},
 pages = {IV:4176},
 title = {Auditory-Modeling Inspired Methods of Feature Extraction for Robust Automatic Speech Recognition},
 year = {2002}
}

@inproceedings{omar2002maximum,
 author = {Mohammed Kamal Omar and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2002.5743659},
 keywords = {recognition},
 month = {May},
 pages = {I:81-84},
 title = {Maximum Mutual Information Based Acoustic Features Representation of Phonological Features for Speech Recognition},
 year = {2002}
}

@unpublished{petruncio2002evaluation,
 author = {David Petruncio},
 keywords = {analysis},
 note = {B.S. Thesis, University of Illinois},
 title = {Evaluation of Various Features for Music Genre Classification with Hidden Markov Models},
 year = {2002}
}

@article{hasegawajohnson2002finding,
 address = {Kyoto, Japan},
 author = {Mark Hasegawa-Johnson},
 grant = {NSF 0132900},
 journal = {Accumu Magazine},
 keywords = {recognition},
 pages = {45-47},
 publisher = {Kyoto Computer Gakuin},
 title = {Finding the Best Acoustic Measurements for Landmark-Based Speech Recognition},
 volume = {11},
 year = {2002}
}

@mastersthesis{jing2002voice,
 author = {Zhinian Jing},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Voice Index and Frame Index for Recognition of Digits in Speech Background},
 year = {2002}
}

@article{beauchamp2001acoustics,
 author = {James Beauchamp and Heinrich Taube and Sever Tipei and Scott Wyatt and Lippold Haken and Mark Hasegawa-Johnson},
 journal = {J. Acoust. Soc. Am.},
 keywords = {analysis},
 number = {5},
 pages = {2961},
 title = {Acoustics, Audio, and Music Technology Education at the University of Illinois},
 url = {https://asa.scitation.org/doi/abs/10.1121/1.4776867},
 volume = {110},
 year = {2001}
}

@unpublished{hasegawa-johnson2001preliminary,
 author = {Mark Hasegawa-Johnson},
 grant = {NIH 0032301},
 keywords = {analysis},
 note = {Unpublished presentation at Universities of Illinois Inter-campus Biomedical Imaging Forum},
 title = {Preliminary Work and Proposed Continuation: Imaging of Speech Anatomy and Behavior.},
 year = {2001}
}

@inproceedings{omar2001gaussian,
 author = {Mohammed K. Omar and Mark Hasegawa-Johnson and Stephen E. Levinson},
 booktitle = {ASRU},
 doi = {10.1109/ASRU.2001.1034582},
 grant = {NSF 0132900},
 keywords = {recognition},
 title = {Gaussian Mixture Models of Phonetic Boundaries for Speech Recognition},
 year = {2001}
}

@inproceedings{gunawan2001plp,
 address = {Salt Lake City, UT},
 author = {Wira Gunawan and Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2001.940771},
 keywords = {recognition},
 pages = {2.2.1-4},
 title = {PLP Coefficients can be Quantized at 400 bps},
 year = {2001}
}

@article{hasegawa-johnson2000line,
 author = {Mark Hasegawa-Johnson},
 doi = {10.1121/1.429481},
 grant = {NIH DC0032301},
 journal = {Journal of the Acoustical Society of America},
 keywords = {analysis},
 number = {1},
 pages = {457-460},
 title = {Line Spectral Frequencies are the Poles and Zeros of a Discrete Matched-Impedance Vocal Tract Model},
 volume = {108},
 year = {2000}
}

@article{zheng2000three,
 author = {Yanli Zheng and Mark Hasegawa-Johnson},
 grant = {NIH 0032301},
 journal = {ASHA Leader},
 keywords = {analysis},
 number = {16},
 pages = {144},
 title = {Three Dimensional Tongue shape Factor Analysis},
 volume = {5},
 year = {2000}
}

@inproceedings{hasegawajohnson00time,
 author = {Mark Hasegawa-Johnson},
 booktitle = {Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
 doi = {10.21437/ICSLP.2000-769},
 keywords = {analysis},
 pages = {vol. 4, 133-136},
 title = {Time-frequency distribution of partial phonetic information measured using mutual information},
 year = {2000}
}

@inproceedings{hasegawajohnson2000multivariate-state,
 address = {Istanbul},
 author = {Mark Hasegawa-Johnson},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.2000.861822},
 keywords = {recognition},
 pages = {1323-1326},
 title = {Multivariate-State Hidden Markov Models for Simultaneous Transcription of Phones and Formants},
 year = {2000}
}

@inproceedings{huang00signal,
 author = {Jun Huang and Stephen Levinson and Mark Hasegawa-Johnson},
 booktitle = {Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
 doi = {10.21437/ICSLP.2000-384},
 keywords = {synthesis},
 pages = {vol. 2, 775-778},
 title = {Signal approximation in Hilbert space and its application on articulatory speech synthesis},
 year = {2000}
}

@mastersthesis{gunawan2000distributed,
 author = {Wira Gunawan},
 keywords = {recognition},
 school = {University of Illinois},
 title = {Distributed Speech Recognition},
 year = {2000}
}

@mastersthesis{setsu2000articulatory,
 author = {Jul Setsu Cha},
 keywords = {synthesis},
 school = {UCLA},
 title = {Articulatory Speech Synthesis of Female and Male Talkers},
 year = {2000}
}

@inproceedings{hasegawa-johnson1999icppit,
 address = {Lisbon},
 author = {Mark Hasegawa-Johnson and Jul Cha and Shamala Pizza and Katherine Haker},
 booktitle = {International Conference On Public Participation and Information Technology},
 grant = {NIH DC0032301},
 keywords = {analysis},
 pages = {575-584},
 title = {CTMRedit: A case study in human-computer interface design},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=4bc8af525ca1f09e6cdc7c5399f382906d3a5365},
 year = {1999}
}

@inproceedings{hasegawa-johnson1999embs,
 author = {Mark Hasegawa-Johnson and Jul Cha and Katherine Haker},
 booktitle = {21st Annual International Conference of the IEEE/EMBS Society},
 grant = {NIH 0032301},
 keywords = {analysis},
 pages = {1170},
 title = {CTMRedit: A Matlab-based tool for segmenting and interpolating MRI and CT images in three orthogonal planes},
 year = {1999}
}

@inproceedings{hasegawa-johnson1999combining,
 address = {Orlando, FL},
 author = {Mark Hasegawa-Johnson},
 booktitle = {International Conference On Signal Processing Applications and Technology},
 grant = {NIH 0032301},
 keywords = {analysis},
 pages = {81.1-5},
 title = {Combining magnetic resonance image planes in the Fourier domain for improved spatial resolution},
 url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=2444cdb69b01fcd889bfc3545f97637fbc330ac6},
 year = {1999}
}

@misc{taniguchi1998speech,
 abstract = {Transform stochastic codebook so that, after perceptual weighting, it will be orthogonal to the adaptive codebook},
 author = {Tomohiko Taniguchi and Mark Johnson},
 howpublished = {United States Patent Number 5799131},
 keywords = {synthesis},
 month = {August},
 title = {Speech coding and decoding system},
 url = {https://patentimages.storage.googleapis.com/5e/54/26/3ff3894828a9d3/US5799131.pdf},
 year = {1998}
}

@article{hasegawa-johnson1998electromagnetic,
 author = {Mark Hasegawa-Johnson},
 doi = {10.1121/1.423775},
 grant = {NIH 0032301},
 journal = {Journal of the Acoustics Society of America},
 keywords = {analysis},
 pages = {2529-2532},
 title = {Electromagnetic Exposure Safety of the Carstens Articulograph AG100},
 volume = {104},
 year = {1998}
}

@article{takayanagi1997information,
 author = {Sumiko Takayanagi and Mark Hasegawa-Johnson and Laurie S. Eisner and Amy Schaefer-Martinez},
 journal = {J. Acoust. Soc. Am.},
 keywords = {analysis},
 pages = {3091},
 title = {Information theory and variance estimation techniques in the analysis of category rating data and paired comparisons},
 volume = {102},
 year = {1997}
}

@phdthesis{johnson1996formant,
 author = {Mark A. Hasegawa-Johnson},
 keywords = {analysis},
 school = {MIT},
 title = {Formant and Burst Spectral Measurements with Quantitative Error Models for Speech Sound Classification},
 url = {https://dspace.mit.edu/handle/1721.1/10636},
 year = {1996}
}

@article{hasegawajohnson1995burst,
 author = {Mark A. Hasegawa-Johnson},
 doi = {10.1121/1.414301},
 journal = {J. Acoust. Soc. Am.},
 keywords = {analysis},
 pages = {2890},
 title = {Burst spectral measures and formant frequencies can be used to accurately discriminate stop place of articulation},
 url = {https://asa.scitation.org/doi/pdf/10.1121/1.414301},
 volume = {98},
 year = {1995}
}

@misc{taniguchi1994speech,
 author = {Tomohiko Taniguchi and Mark Johnson and Yasuji Ohta and Hideki Kurihara and Yoshinori Tanaka and Yoshihito Sakai},
 howpublished = {United States Patent Number 5323486},
 keywords = {synthesis},
 month = {June},
 title = {Speech coding system having codebook storing differential vectors between each two adjoining code vectors},
 url = {https://patentimages.storage.googleapis.com/6e/ac/fb/78352f241fd201/US5323486.pdf},
 year = {1994}
}

@article{johnson1994a,
 author = {Mark A. Johnson},
 journal = {MIT Speech Communication Group Working Papers},
 keywords = {analysis},
 pages = {94-105},
 title = {A mapping between trainable generalized properties and the acoustic correlates of distinctive features},
 volume = {9},
 year = {1994}
}

@inproceedings{johnson1994automatic,
 address = {Yokohama},
 author = {Mark Johnson},
 booktitle = {ICSLP},
 doi = {10.21437/ICSLP.1994-424},
 keywords = {analysis},
 pages = {1639-1643},
 title = {Automatic context-sensitive measurement of the acoustic correlates of distinctive features},
 year = {1994}
}

@misc{taniguchi1993speech1,
 abstract = {hexagonal lattice},
 author = {Tomohiko Taniguchi and Mark Johnson},
 howpublished = {United States Patent Number 5245662},
 keywords = {synthesis},
 month = {September},
 title = {Speech coding system},
 url = {https://patentimages.storage.googleapis.com/67/19/4e/63aa5e1e86ae4e/US5245662.pdf},
 year = {1993}
}

@misc{taniguchi1993speech2,
 abstract = {sparse adaptive codebook},
 author = {Tomohiko Taniguchi and Mark Johnson and Hideki Kurihara and Yoshinori Tanaka and Yasuji Ohta},
 howpublished = {United States Patent Number 5199076},
 keywords = {synthesis},
 month = {March},
 title = {Speech coding and decoding system},
 url = {https://patentimages.storage.googleapis.com/f5/8e/8f/fb388df1a25c93/US5199076.pdf},
 year = {1993}
}

@article{johnson1993a,
 author = {Mark A. Johnson},
 doi = {10.1121/1.407629},
 journal = {J. Acoust. Soc. Am.},
 keywords = {analysis},
 pages = {1865},
 title = {A mapping between trainable generalized properties and the acoustic correlates of distinctive features},
 url = {https://asa.scitation.org/doi/pdf/10.1121/1.407629},
 volume = {94},
 year = {1993}
}

@article{johnson1992using,
 author = {Mark A. Johnson},
 journal = {J. Acoust. Soc. Am.},
 keywords = {analysis},
 pages = {2420-2421},
 title = {Using beam elements to model the vocal fold length in breathy voicing},
 volume = {91},
 year = {1992}
}

@article{johnson1992analysis,
 author = {Mark A. Johnson},
 journal = {MIT Speech Communication Group Working Papers},
 keywords = {analysis},
 pages = {29-42},
 title = {Analysis of durational rhythms in two poems by Robert Frost},
 volume = {8},
 year = {1992}
}

@article{johnson1992on-line,
 author = {Mark Johnson and Tomohiko Taniguchi},
 doi = {10.1109/78.149977},
 journal = {IEEE Transactions Acoustics, Speech, and Signal Processing},
 keywords = {synthesis},
 pages = {2090-2093},
 title = {On-line and off-line computational reduction techniques using backward filtering in CELP speech coders},
 volume = {40},
 year = {1992}
}

@inproceedings{johnson1991low-complexity,
 address = {Toronto, Canada},
 author = {Mark A. Johnson and Tomohiko Taniguchi},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.1991.150317},
 keywords = {synthesis},
 pages = {221-224},
 title = {Low-complexity multi-mode VXC using multi-stage optimization and mode selection},
 year = {1991}
}

@inproceedings{taniguchi1991pitch,
 address = {Toronto, Canada},
 author = {Tomohiko Taniguchi and Mark A. Johnson and Yasuji Ohta},
 booktitle = {ICASSP},
 doi = {10.1109/ICASSP.1991.150322},
 keywords = {synthesis},
 pages = {241-244},
 title = {Pitch sharpening for perceptually improved CELP, and the sparse-delta codebook for reduced computation},
 year = {1991}
}

@inproceedings{taniguchi1991improving,
 address = {Singapore},
 author = {Tomohiko Taniguchi and Fumio Amano and Mark A. Johnson},
 booktitle = {International Symposium on Circuits and Systems},
 doi = {10.1109/ISCAS.1991.176404},
 keywords = {synthesis},
 title = {Improving the performance of CELP-based speech coding at low bit rates},
 year = {1991}
}

@inproceedings{johnson1990computational,
 address = {Hakata},
 author = {Mark A. Johnson and Tomohiko Taniguchi},
 booktitle = {Institute of Electr. and Information and Comm. Eng. Symposium DSP 90-15},
 keywords = {synthesis},
 pages = {61-66},
 title = {Computational reduction in sparse-codebook CELP using backward-weighting of the input},
 year = {1990}
}

@inproceedings{taniguchi1990multi-vector,
 address = {Kobe},
 author = {Tomohiko Taniguchi and Mark A. Johnson and Yasuji Ohta},
 booktitle = {ICSLP},
 doi = {10.21437/ICSLP.1990-29},
 keywords = {synthesis},
 pages = {113-116},
 title = {Multi-vector pitch-orthogonal LPC: quality speech with low complexity at rates between 4 and 8 kbps},
 year = {1990}
}

@inproceedings{johnson1990pitch-orthogonal,
 address = {San Diego, CA},
 author = {Mark A. Johnson and Tomohiko Taniguchi},
 booktitle = {IEEE Global Telecommunications Conference (GLOBECOM)},
 doi = {10.1109/GLOCOM.1990.116570},
 keywords = {synthesis},
 pages = {542-546},
 title = {Pitch-orthogonal code-excited LPC},
 year = {1990}
}