2004 SST Group Presentations

2004

• Source Separation Using Particle Filters, Mital Gandhi and Mark Hasegawa-Johnson, Interspeech 2004
• Creating Acoustic/Articulatory/Prosodic Feature Templates for Words, Vidya Mohan
• Landmark-Based Speech Recognition: The Marriage of High-Dimensional Machine Learning Techniques with Modern Linguistic Representations, Mark Hasegawa-Johnson, James Baker, Sarah Borys, Ken Chen, Emily Coogan, Steven Greenberg, Amit Juneja, Katrin Kirchhoff, Karen Livescu, Srividya Mohan, Jen Muller, Kemal Sonmez, and Tianyu Wang
• Speech Recognition Models of the Interdependence Among Prosody, Syntax, and Segmental Acoustics, Mark Hasegawa-Johnson, Jennifer Cole, Chilin Shih, Ken Chen, Aaron Cohen, Sandra Chavarria, Heejin Kim, Taejin Yoon, Sarah Borys, and Jeung-Yoon Choi
• Acoustic Landmarks and Articulatory Phonology for Automatic Speech Recognition, Mark Hasegawa-Johnson, Language Processing Brownbag, 9/2004
• DSP and Particle Filter Techniques for Formant Tracking and Sound Classification, Yanli Zheng and Mark Hasegawa-Johnson, ICASSP 2004
• Figure: Prosody-Dependent Speech Recognition, Ken Chen
• Landmark-Based Speech Recognition: Report of the Workshop Group, 8/16/2004, Mark Hasegawa-Johnson, James Baker, Steven Greenberg, Katrin Kirchhoff, Jen Muller, Kemal Sonmez, Sarah Borys, Ken Chen, Amit Juneja, Karen Livescu, Srividya Mohan, Emily Coogan, Tianyu Wang
• Modeling and Recognition of Phonetic and Prosodic Factors for Improvements to Speech Recognition Models, Sarah Borys, Mark Hasegawa-Johnson, Jennifer Cole and Aaron Cohen, Interspeech 2004
• A Feature-Based Model of Human Lexical Access, Kenneth N. Stevens, in collaboration with Jay Keyser, Sharon Manuel, Stefanie Shattuck-Hufnagel, Janet Slifka, Atiwong Suchato, presentation at the Johns Hopkins summer workshop 2004
• From Lattices to Landmarks: Dictionary-Based Methods, Mark Hasegawa-Johnson
• Vowel Nasalization Detection, Tianyu (Tom) Wang
• Landmark-Based Speech Recognition, Mark Hasegawa-Johnson, Jim Baker, Steven Greenberg, Katrin Kirchhoff, Jen Muller, Kemal Sonmez, Ken Chen, Amit Juneja, Karen Livescu, Srividya Mohan, Sarah Borys, Tarun Pruthi, Emily Coogan, Tianyu Wang
• Modeling pronunciation variation using artificial neural networks for English spontaneous speech, Ken Chen and Mark Hasegawa-Johnson, Interspeech 2004
• Experiments in Landmark-Based Speech Recognition, Mark Hasegawa-Johnson, Sarah Borys, and Ken Chen
• A Maximum Likelihood Prosody Recognizer, Ken Chen, Mark Hasegawa-Johnson, Aaron Cohen
• Cross Validation of SVMs for Acoustic Feature Classification using Entire Regularization Path, Tianyu Tom Wang
• Schematic: Lattice-Based Landmark Rescoring
• Modeling pronunciation variation using artificial neural networks for English spontaneous speech, Ken Chen and Mark Hasegawa-Johnson
• Maximum Entropy Techniques for min-WER Score Combination with Sausages, Kemal Sonmez
• Landmark-Based Speech Recognition: Status Report, 7/21/2004, Mark Hasegawa-Johnson, Katrin Kirchhoff, Sarah Borys, Amit Juneja, Kemal Sonmez
• A Factorial HMM Approach to Robust Speech Recognition in Non-Stationary Noise, Ameya Deoras and Mark Hasegawa-Johnson
• Glottalization and Vowel Nasalization Detection, Tianyu Tom Wang
• How Prosody Improves Word Recognition, Ken Chen and Mark Hasegawa-Johnson, Speech Prosody 2004
• ws04_Landmark-Based_Speech_Recognition_highlights.ppt
• Automatic Detection of Contrast for Speech Understanding, Tong Zhang, Mark Hasegawa-Johnson, Stephen E. Levinson, Interspeech 2004
• Children’s Emotion Recognition in an Intelligent Tutoring Scenario, Tong Zhang, Mark Hasegawa-Johnson, Stephen E. Levinson, Interspeech 2004