S3.1: AGGLOMERATIVE INFORMATION BOTTLENECK FOR SPEAKER DIARIZATION OF MEETINGS DATA
Deepu Vijayasenan, Fabio Valente, Herve Boulard, IDIAP Research Institute, Switzerland
S3.2: EFFICIENT COMBINATION OF PARAMETRIC SPACES, MODELS AND METRICS FOR SPEAKER DIARIZATION - A MAXIMUM ENTROPY APPROACH
Themos Stafylakis, Vassilis Katsouros, George Carayannis, Athena - Research and Innovation Center in Information, Communication and Knowledge Technologies, Greece
S3.3: ROBUST SPEAKER CLUSTERING STRATEGIES TO DATA SOURCE VARIATION FOR IMPROVED SPEAKER DIARIZATION
Kyu Han, Samuel Kim, Shrikanth Narayanan, University of Southern California, United States
S3.4: A STUDY ON SOFT MARGIN ESTIMATION FOR LVCSR
Jinyu Li, Georgia Institute of Technology, United States; Zhijie Yan, University of Science and Technology of China, China; Chin-Hui Lee, Georgia Institute of Technology, United States; Ren-Hua Wang, University of Science and Technology of China, China
S3.5: HIERARCHICAL LARGE-MARGIN GAUSSIAN MIXTURE MODELS FOR PHONETIC CLASSIFICATION
Hung-An Chang, James Glass, Massachusetts Institute of Technology, United States
S3.6: AUTOMATIC SPEECH RECOGNITION BASED ON WEIGHTED MINIMUM CLASSIFICATION ERROR (W-MCE) TRAINING METHOD
Qiang Fu, Biing-Hwang Juang, Georgia Institute of Technology, United States
S3.7: TRAINING DATA SELECTION FOR IMPROVING DISCRIMINATIVE TRAINING OF ACOUSTIC MODELS
Shih-Hung Liu, Fang-Hui Chu, Shih-Hsiang Lin, Hung-Shin Lee, Berlin Chen, National Taiwan Normal University, Taiwan
S3.8: A CONSTRAINED LINE SEARCH APPROACH TO GENERAL DISCRIMINATIVE HMM TRAINING
Peng Liu, Microsoft Research Asia, China; Cong Liu, University of Science and Technology of China, China; Hui Jiang, York University, China; Frank Soong, Ren-Hua Wang, Microsoft Research Asia, China
S3.9: MIXTURE GAUSSIAN HMM-TRAJCTORY METHOD USING LIKELIHOOD COMPENSATION
Yasuhiro Minami, NTT Corporation, Japan
S3.10: STATE-DEPENDENT MIXTURE TYING WITH VARIABLE CODEBOOK SIZE FOR ACCENTED SPEECH RECOGNITION
Yi Liu, Fang Zheng, Center for Speech and Language Technologies, China; Lei He, Toshiba (China) Research and Development Center, China; Yunqing Xia, Center for Speech and Language Technologies, China
S3.11: BROAD PHONETIC CLASS RECOGNITION IN A HIDDEN MARKOV MODEL FRAMEWORK USING EXTENDED BAUM-WELCH TRANSFORMATIONS
Tara Sainath, Massachusetts Institute of Technology, United States; Dimitri Kanevsky, Bhuvana Ramabhadran, IBM T. J. Watson Research Center, United States
S3.12: A COMPACT SEMIDEFINITE PROGRAMMING (SDP) FORMULATION FOR LARGE MARGIN ESTIMATION OF HMMS IN SPEECH RECOGNITION
Yan Yin, Hui Jiang, York University, Canada
S3.13: HMM TRAINING BASED ON CV-EM AND CV GAUSSIAN MIXTURE OPTIMIZATION
Takahiro Shinozaki, Tatsuya Kawahara, Kyoto University, Japan
S3.14: VARIATIONAL KULLBACK-LEIBLER DIVERGENCE FOR HIDDEN MARKOV MODELS
John Hershey, Peder Olsen, Steven Rennie, IBM T. J. Watson Research Center, United States
S3.15: BAYESIAN ADAPTATION IN HMM TRAINING AND DECODING USING A MIXTURE OF FEATURE TRANSFORMS
Stavros Tsakalidis, Spyros Matsoukas, BBN Technologies, United States
S3.16: USE OF SYLLABLE NUCLEI LOCATIONS TO IMPROVE ASR
Chris Bartels, Jeff Bilmes, University of Washington, United States
S3.17: SPEECH RECOGNITION WITH LOCALIZED TIME-FREQUENCY PATTERN DETECTORS
Ken Schutte, James Glass, MIT Computer Science and Artificial Intelligence Laboratory, United States
S3.18: REGULARIZATION, ADAPTATION, AND NON-INDEPENDENT FEATURES IMPROVE HIDDEN CONDITIONAL RANDOM FIELDS FOR PHONE CLASSIFICATION
Yun-Hsuan Sung, Constantinos Boulis, Christopher Manning, Dan Jurafsky, Stanford University, United States
S3.19: DISCRIMINATIVE TRAINING OF MULTI-STATE BARGE-IN MODELS
Andrej Ljolje, Vincent Goffin, AT&T Labs - Research, United States
S3.20: GRAPH-BASED LEARNING FOR PHONETIC CLASSIFICATION
Andrei Alexandrescu, Katrin Kirchhoff, University of Washington, United States