2003 SST Group Presentations

2003

• Multimodal ASR in Cars, Mark Hasegawa-Johnson, Tom Huang, Steve Levinson, Bowon Lee, Danfeng Li, Ming Liu
• Landmark-Based Speech Recognition: Summary Figure
• What Is Signal Processing? Mark Hasegawa-Johnson, ECE Advising Fair
• Speech and Language Engineering at the University of Illinois, Mark Hasegawa-Johnson, Jont Allen, Jennifer Cole, Thomas Huang, Stephen Levinson, Dan Roth, Richard Sproat
• AVSR Experiments, Stephen M. Chu
• Prosody Dependent Speech Recognition with Explicit Duration Modelling at Intonational Phrase Boundaries, K. Chen, S. Borys, M. Hasegawa-Johnson, and J. Cole, Eurospeech 2003
• Figures for PARAFAC Analysis of the Three dimensional tongue Shape,, Yanli Zheng, Mark Hasegawa-Johnson, and Shamala Pizza, JASA 2003
• Figures for Automatic Recognition of Pitch Movements Using Multilayer Perceptron and Time-Delay Recursive Neural Network, Sung-Suk Kim, Mark Hasegawa-Johnson, and Ken Chen, Signal Processing Letters 2004
• Audiovisual Display and Audiovisual Recognition in Free Field Environments: Caves, Cars, and Critical Bands, Mark Hasegawa-Johnson, Bowon Lee, Camille Goudeseune, Zhinian Jing, Danfeng Li, Thomas Huang, Stephen Levinson
• Speech Recognition and Speech Production Research Relevant to the Automatic Recognition of Dysarthric Speech, Jennifer Cole, Mark Hasegawa-Johnson, Steve Levinson
• Landmark-Based Speech Recognition: Proposal for a Johns Hopkins Workshop, Mark Hasegawa-Johnson, Carol Espy-Wilson, Jim Glass, Steve Greenberg, Katrin Kirchhoff, Mark Liberman, Partha Niyogi, Ken Stevens
• The Landmark-Based Speech Recognition Proposal, in 3 Minutes
• Landmark-Based Speech Recognition: Psychological and Phonetic Foundations, Engineering Problems, Bayesian Solutions, Mark Hasegawa-Johnson
• Open-Loop Dereverberation of Multichannel Room Impulse Responses, Bowon Lee, Mark A. Hasegawa-Johnson, and Camille Goudeseune, ASA 2003
• Bringing Prosody into Automatic Speech Recognition: Improving word recognition and advancing linguistic science, Jennifer Cole and Mark Hasegawa-Johnson, Language Processing Brownbag, 2003
• Prosody dependent language modeling based on the correlation between prosody and syntax, Ken Chen and Mark Hasegawa-Johnson, ASRU 2003
• Prosody and Speech Recognition, Mark Hasegawa-Johnson, Jennifer Cole, Ken Chen, Aaron Cohen, Jeung-Yoon Choi, Sarah Borys, Mohamed Omar, Yanli Zheng, Hansook Choi, Heejin Kim, Sung-Suk Kim, Beckman Open House, 2003
• The Importance of Prosodic Factors in Phoneme Modeling with Applications to Speech Recognition, Mark Hasegawa-Johnson
• Speech Recognition as a Pattern Matching Problem, Mark Hasegawa-Johnson
• Pitch Accent Recognition Using Recurrent Neural Network, Sung-Suk Kim
• Bayesian Learning for Models of Human Speech Perception, Mark Hasegawa-Johnson
• Landmark Detection and Asynchronous Distinctive Feature Modeling, Mark Hasegawa-Johnson, Jim Baker, Steve Greenberg, Katrin Kirchhoff, Carol Espy-Wilson, Amit Juneja, Jim Glass, Karen Livescu, Min Tang, Mark Liberman, Partha Niyogi, Ken Stevens