SP-P12: Acoustic Modeling II |
| Session Type: Poster |
| Time: Friday, March 30, 10:30 - 12:30 |
| Location: Poster Area A
|
| Session Chairs: Peter Li, Li Creative Technologies, Inc. and Seiichi Yamamoto, Doshisha University
|
| |
|
SP-P12.1: AN INVESTIGATION OF TIED-MIXTURE GMM BASED TRIPHONE STATE CLUSTERING
|
| Guangsen Wang; National University of Singapore
|
| Khe Chai Sim; National University of Singapore
|
| |
|
SP-P12.2: REVISITING SEMI-CONTINUOUS HIDDEN MARKOV MODELS
|
| Korbinian Riedhammer; University Erlangen-Nuremberg
|
| Tobias Bocklet; University Erlangen-Nuremberg
|
| Arnab Ghoshal; University of Edinburgh
|
| Daniel Povey; Microsoft Research
|
| |
|
SP-P12.3: SPECTROGRAPHIC SEAM PATTERNS FOR DISCRIMINATIVE WORD SPOTTING
|
| Shubhranshu Barnwal; Indian Institute of Technology, Kanpur
|
| Kamal Sahni; Indian Institute of Technology, Kanpur
|
| Rita Singh; Carnegie Mellon University
|
| Bhiksha Raj; Carnegie Mellon University
|
| |
|
SP-P12.4: A CHUNK-BASED PHONETIC SCORE FOR MOBILE VOICE SEARCH
|
| Rohit Prabhavalkar; The Ohio State University
|
| Jasha Droppo; Microsoft Research
|
| |
|
SP-P12.5: ADAPTIVE BOOSTING FEATURES FOR AUTOMATIC SPEECH RECOGNITION
|
| Kham Nguyen; Northeastern University
|
| Tim Ng; BBN Technologies
|
| Long Nguyen; BBN Technologies
|
| |
|
SP-P12.6: LOW RESOURCE SPEECH RECOGNITION WITH AUTOMATICALLY LEARNED SPARSE INVERSE COVARIANCE MATRICES
|
| Weibin Zhang; Hong Kong University of Science and Technology
|
| Pascale Fung; Hong Kong University of Science and Technology
|
| |
|
SP-P12.7: IMPROVED TONE MODELING BY EXPLOITING ARTICULATORY FEATURES FOR MANDARIN SPEECH RECOGNITION
|
| Hao Chao; Chinese Academy of Sciences
|
| Zhanlei Yang; Chinese Academy of Sciences
|
| Wenju Liu; Chinese Academy of Sciences
|
| |
|
SP-P12.8: DISCRIMINATIVE TRAINING FOR SPEECH RECOGNITION IS COMPENSATING FOR STATISTICAL DEPENDENCE IN THE HMM FRAMEWORK
|
| Dan Gillick; International Computer Science Institute
|
| Steven Wegmann; International Computer Science Institute
|
| Larry Gillick; EnglishCentral, Inc.
|
| |
|
SP-P12.9: DISCRIMINATIVE DYNAMIC GAUSSIAN MIXTURE SELECTION WITH ENHANCED ROBUSTNESS AND PERFORMANCE FOR MULTI-ACCENT SPEECH RECOGNITION
|
| Chao Zhang; Tsinghua University
|
| Yi Liu; Tsinghua University
|
| Yunqing Xia; Tsinghua University
|
| Chin-Hui Lee; Georgia Institute of Technology
|
| |
|
SP-P12.10: DISCRIMINATIVE FEATURE TRANSFORMS USING DIFFERENCED MAXIMUM MUTUAL INFORMATION
|
| Marc Delcroix; NTT Communication Science Laboratories
|
| Atsunori Ogawa; NTT Communication Science Laboratories
|
| Shinji Watanabe; NTT Communication Science Laboratories
|
| Tomohiro Nakatani; NTT Communication Science Laboratories
|
| Atsushi Nakamura; NTT Communication Science Laboratories
|
| |
|
SP-P12.11: AN INTEGRATED APPROACH TO FEATURE COMPENSATION COMBINING PARTICLE FILTERS AND HIDDEN MARKOV MODELS FOR ROBUST SPEECH RECOGNITION
|
| Aleem Mushtaq; Georgia Institute of Technology
|
| Chin Hui-Lee; Georgia Institute of Technology
|
| |
|
SP-P12.12: IMPLICIT TRAJECTORY MODELLING USING TEMPORALLY VARYING WEIGHT REGRESSION FOR AUTOMATIC SPEECH RECOGNITION
|
| Shilin Liu; National University of Singapore
|
| Khe Chai Sim; National University of Singapore
|
| |