For more information
- Ph.D., Elec. Eng. & Comp. Sc., MIT, 1996
Mark Hasegawa-Johnson has been on the faculty at the University of Illinois since 1999, where he is currently a Professor of Electrical and Computer Engineering. He received his Ph.D. in 1996 at MIT, with a thesis titled "Formant and Burst Spectral Measures with Quantitative Error Models for Speech Sound Classification," after which he was a post-doc at UCLA from 1996-1999. Prof. Hasegawa-Johnson is a Fellow of the Acoustical Society of America, and a Senior Member of IEEE and ACM. He is currently Treasurer of ISCA, and Senior Area Editor of the IEEE Transactions on Audio, Speech and Language. He has published 280 peer-reviewed journal articles and conference papers in the general area of automatic speech analysis, including machine learning models of articulatory and acoustic phonetics, prosody, dysarthria, non-speech acoustic events, audio source separation, and under-resourced languages.
Professor Hasegawa-Johnson typically teaches Artificial Intelligence (CS 440/ECE 448), Multimedia Signal Processing (ECE 417), and Speech and Image Analysis (ECE 401). He has also taught Speech Processing (ECE 537), Digital Signal Processing (ECE 551), Audio Engineering (ECE 403), Pattern Recognition (ECE 544NA), and Probability (ECE 313).
Dr. Hasegawa-Johnson's research is focused on the area of automatic speech recognition, with a particular focus on the mathematization of linguistic concepts. In the past five years, Dr. Hasegawa-Johnson's group has developed mathematical models of concepts from linguistics including a rudimentary model of pre-conscious speech perception (the landmark-based speech recognizer), a model that interprets pronunciation variability by figuring out how the talker planned his or her speech movements (tracking of tract variables from acoustics, and of gestures from tract variables), and a model that uses the stress and rhythm of natural language (prosody) to disambiguate confusable sentences. Recent application successes include:
* Speech recognition for talkers with cerebral palsy. The automatic system, suitably constrained, outperforms a human listener.
* Retrieval of broadcast television segments in four languages, based on queries specified in the international phonetic alphabet. The Illinois team, including students of Prof. Hasegawa-Johnson and Prof. Huang, took third place in this international competition, and was the only finalist from the United States.
* Automatic detection and labeling of non-speech audio events. The Illinois team, including students of Prof. Hasegawa-Johnson and Prof. Huang, took first place in this international competition.
* Teaching Chinese. Software and methods developed by Prof. Hasegawa-Johnson, together with his colleagues from Linguistics and Psychology, are being tested in Mandarin language classrooms at the University of Illinois.
Undergraduate Research Opportunities
Professor Hasegawa-Johnson typically supervises one or two undergraduate research projects per year, thesis research preferred. Past student theses include automatic recognition of musical genre, factorial HMMs for the automatic recognition of speech in music backgrounds, prosody-dependent speech recognition, image source modeling of room impulse response, sonorancy classification for automatic language ID, phonetic landmark detection for automatic language ID, and digital field recorder for acquisition of a natural audio database.
- Acoustic phonetics, Audio signal processing and speech recognition, Speech and auditory physiology.
- Daily Illini List of Teachers Ranked as Excellent by Their Students. Fall 2006 (ECE 544NA, Pattern Recognition), Spring 2004 (ECE 303, Audio Engineering), Spring 2003 (ECE 303, Audio Engineering), Spring 2002 (ECE 303, Audio Engineering), Spring 2001 (ECE 303, Audio Engineering)
- Eminent Initiate, Alpha Chapter of Eta Kappa Nu (University of Illinois), May 3, 2003. Co-chapter-advisor, 2003-4. Chapter Advisor, 2004-6.
- Principal Investigator, "Landmark Detection for LVCSR," Johns Hopkins CLSP Summer Workshop WS04, July and August, 2004. Funded by NSF, NSA, and DARPA; JHU PI is Fred Jelinek.
- NSF CAREER Award, 1/1/2002-12/31/2007
- Individual National Research Service Award, National Institutes of Health, 1998-1999.
- Frederic Vinton Hunt Post-Doctoral Fellowship, Acoustical Society of America, 1996-1997.
- Who's Who in America (national biography listing), 2006-10. Who's Who in Science and Engineering, 1992.
- Paul L. Fortescue Graduate Fellow, IEEE, 1988-1989.
- CS 440 - Artificial Intelligence
- ECE 401 - Signal and Image Analysis
- ECE 417 - Multimedia Signal Processing
- ECE 448 - Artificial Intelligence
- ECE 498 - Special Topics in ECE
- ECE 537 - Speech Processing Fundamentals
- ECE 544 - Pattern Recognition
- ECE 590 - Speech