Faculty

Institution

Unit

Venue

Mark Hasegawa-Johnson

Professor

UIUC

Affiliations

The Grainger College of Engineering

Department of Electrical and Computer Engineering

Electrical & Computer Engineering

Mark Hasegawa-johnson is currently serving as an Electrical And Computer Engineering Professor at Uiuc.

Honors

Create free account to unlock more features

Experiences

Create free account to unlock more features

Education

Create free account to unlock more features

Mark Hasegawa-Johnson

UIUC

Professor

You can click a keyword to filter the displayed items

speech processing speech recognition speech communication spoken language technology language linguistics natural language processing machine learning spoken language processing phonetics speech perception data science computer science speech technology phonology signal processing machine learning research robust speech recognition speech analysis deep learning speech acoustics speech science voice recognition speech production acoustic modeling speech synthesis language recognition speech output image representation prosody (linguistics) speech corpus semantic evaluation multi-speaker speech recognition distant speech recognition multimedia information processing speech input speaker recognition neurolinguistics audio analysis computational intelligence language resources hearing research speech separation pathological speech machine vision applied linguistics acoustic signal processing information fusion automatic speech recognition affective computing multimedia modeling speech enhancement speech sound disorders speaker diarization recurrent neural networks feature learning cross-lingual representation source separation audio retrieval speech motor control convolutional neural networks mutual information speech signal cerebral palsy acoustic cues gaussian mixture models word error rate radio news speech asr system acoustic landmarks gaussian mixture model mismatched crowdsourcing voice quality hidden markov models semantic image inpainting monaural source separation acoustic phonetics audio signal processing

Video Presentations

Notable Scholarly Works

Notable Federal Grants

Collaborators

Cohort-Sensitive Labeling: An Effective Approach for Enhancing Asr Performance. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Jonghwan NaMark Hasegawa-JohnsonBowon Lee

biostatisticscohort studiesbiomedical informaticsasr performancepersonalized medicine

Dysarthric Speech Conformer: Adaptation for Sequence-To-Sequence Dysarthric Speech Recognition. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Qianli WangZihan ZhongSatwinder SinghClarion MendesMark Hasegawa-JohnsonWaleed AbdullaSeyed Reza Shahamiri

linguisticsspeech processingpathological speechspeech analysisspeech sciencedysarthric speech conformerspeech recognitionspeech communication

Improved Recognition of the Speech of People With Parkinson’s Who Stutter. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Jonghwan NaXiuwen ZhengBowon LeeMark Hasegawa-Johnson

communication disordersfluency disordersspeech fluency disorderneurolinguisticsspeech motor controlspeech processingparkinson's diseaselanguage processing in the brainmovement disordersspeech perceptionpathological speechspeech analysislanguagespeech recognitionspeech communicationrehabilitationstuttering

Introduction to Special Issue on Acoustic Cue-Based Perception and Production of Speech by Humans and Machines. The Journal of the Acoustical Society of America (2025)

Stefanie Shattuck-HufnagelMaria-Gabriella Di BenedettoAbeer AlwanMark Hasegawa-Johnson

psychoacousticsacoustic cue-based perceptionspoken language technologykenneth n. stevenssoundspeech processingspeech technologyspeech perceptionlanguagespecial issuemusicphoneticsspeech communicationspeech acoustics

Limmits'24: Multi-Speaker, Multi-Lingual Indic Tts With Voice Cloning. IEEE Open Journal of Signal Processing (2025)

Sathvik UdupaJesuraja BandekarAbhayjeet SinghDeekshitha GSaurabh KumarSandhya BadigerAmala NagireddiRoopa RPrasanta Kumar GhoshHema A MurthyPranaw KumarKeiichi TokudaMark Hasegawa-JohnsonPhilipp Olbrich

speech synthesislinguisticsspeech processingspeech corpusspeech recognitionspeech outputspeech communication

Limmits’25: Multilingual Streaming Tts With Neural Codecs for Indian Languages. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Philipp OlbrichHema A MurthyPranaw KumarShinji WatanabeSheng ZhaoMark Hasegawa-Johnson

spoken language technologylinguisticscross-lingual representationspeech processingindian languagescomputational linguisticsreal-time languagenatural language processinglanguagelanguage modelsmultilingualismspeech translationlanguage recognition

Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Satwinder SinghQianli WangZihan ZhongClarion MendesMark Hasegawa-JohnsonWaleed AbdullaSeyed Reza Shahamiri

spoken language technologyrobust cross-etiologyspeech processingpathological speechspeech analysisspeech sciencelanguagespeech recognition

Speech AI for All: Promoting Accessibility, Fairness, Inclusivity, and Equity. (2025)

Shaomei WuKimi WenzelJingjin LiQisheng LiAlisha PradhanRaja KushalnagarColin LeaAllison KoeneckeChristian VoglerMark Hasegawa-JohnsonNorman Makoto SuNan Bernstein Ratner

artificial intelligencespoken language technologyvoice technologyspeech interfacesspeech processingspeech aispeech analysiscommunicationfairnesslanguagespeech recognitionspeech technologyspeech communication

Speech-Based Phonetic Transcript Metrics. IEEE Transactions on Audio Speech and Language Processing (2025)

Heting GaoMark Hasegawa-JohnsonChang D. Yoo

phonologylinguisticsspeech processingspeech analysiscorpus linguisticsspeech corpuslanguagespeech recognitionspoken language processingphoneticsspeech communication

SYNCDIFF: Diffusion-Based Talking Head Synthesis With Bottlenecked Temporal Visual Prior for Improved Synchronization. 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (2025)

Xulin FanHeting GaoZiyi ChenPeng ChangMei HanMark Hasegawa-Johnson

neural computationspoken language technologyspeech synthesisvisual perceptionsystems neuroscienceattentionhuman image synthesisspeech processingneuroscienceimproved synchronizationspeech perceptionvideo synthesizerfacial animationvisual systemcognitive sciencespeech communicationvisual science

1
2
3
4
5
41
10 / page

Mark Hasegawa-Johnson

Professor

UIUC

Affiliations

The Grainger College of Engineering

Department of Electrical and Computer Engineering

Electrical & Computer Engineering

Mark Hasegawa-johnson is currently serving as an Electrical And Computer Engineering Professor at Uiuc.

Honors

Create free account to unlock more features

Experiences

Create free account to unlock more features

Education

Create free account to unlock more features

Mark Hasegawa-Johnson

UIUC

Professor

You can click a keyword to filter the displayed items

Video Presentations

Notable Scholarly Works

Notable Federal Grants

Collaborators

Cohort-Sensitive Labeling: An Effective Approach for Enhancing Asr Performance. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Jonghwan NaMark Hasegawa-JohnsonBowon Lee

biostatisticscohort studiesbiomedical informaticsasr performancepersonalized medicine

Qianli WangZihan ZhongSatwinder SinghClarion MendesMark Hasegawa-JohnsonWaleed AbdullaSeyed Reza Shahamiri

linguisticsspeech processingpathological speechspeech analysisspeech sciencedysarthric speech conformerspeech recognitionspeech communication

Improved Recognition of the Speech of People With Parkinson’s Who Stutter. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Jonghwan NaXiuwen ZhengBowon LeeMark Hasegawa-Johnson

Introduction to Special Issue on Acoustic Cue-Based Perception and Production of Speech by Humans and Machines. The Journal of the Acoustical Society of America (2025)

Stefanie Shattuck-HufnagelMaria-Gabriella Di BenedettoAbeer AlwanMark Hasegawa-Johnson

Limmits'24: Multi-Speaker, Multi-Lingual Indic Tts With Voice Cloning. IEEE Open Journal of Signal Processing (2025)

speech synthesislinguisticsspeech processingspeech corpusspeech recognitionspeech outputspeech communication

Limmits’25: Multilingual Streaming Tts With Neural Codecs for Indian Languages. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Philipp OlbrichHema A MurthyPranaw KumarShinji WatanabeSheng ZhaoMark Hasegawa-Johnson

Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2025)

Satwinder SinghQianli WangZihan ZhongClarion MendesMark Hasegawa-JohnsonWaleed AbdullaSeyed Reza Shahamiri

spoken language technologyrobust cross-etiologyspeech processingpathological speechspeech analysisspeech sciencelanguagespeech recognition

Speech AI for All: Promoting Accessibility, Fairness, Inclusivity, and Equity. (2025)

Shaomei WuKimi WenzelJingjin LiQisheng LiAlisha PradhanRaja KushalnagarColin LeaAllison KoeneckeChristian VoglerMark Hasegawa-JohnsonNorman Makoto SuNan Bernstein Ratner

Speech-Based Phonetic Transcript Metrics. IEEE Transactions on Audio Speech and Language Processing (2025)

Heting GaoMark Hasegawa-JohnsonChang D. Yoo

phonologylinguisticsspeech processingspeech analysiscorpus linguisticsspeech corpuslanguagespeech recognitionspoken language processingphoneticsspeech communication

Xulin FanHeting GaoZiyi ChenPeng ChangMei HanMark Hasegawa-Johnson

1
2
3
4
5
41
10 / page