ICASSP 2010 - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing - March 14 - 19, 2010 - Dallas, Texas, USA

Technical Program

SP-L8: New Algorithms for ASR

Session Type: Lecture
Time: Thursday, March 18, 16:00 - 18:00
Location: Room B
Session Chair: Mark Gales, Cambridge University, UK
 
SP-L8.1: SPEECH MODELING BASED ON COMMITTEE-BASED ACTIVE LEARNING
         Yuzo Hamanaka; Tokyo Institute of Technology
         Koichi Shinoda; Tokyo Institute of Technology
         Sadaoki Furui; Tokyo Institute of Technology
         Tadashi Emori; NEC Information Systems, Ltd.
         Takafumi Koshinaka; NEC Corporation
 
SP-L8.2: PHONE RECOGNITION USING RESTRICTED BOLTZMANN MACHINES
         Abdel-rahman Mohamed; University of Toronto
         Geoffrey Hinton; University of Toronto
 
SP-L8.3: CONTEXT DEPENDENT PHONETIC STRING EDIT DISTANCE FOR AUTOMATIC SPEECH RECOGNITION
         Jasha Droppo; Microsoft Research
         Alex Acero; Microsoft Research
 
SP-L8.4: DETECTION-BASED SPEECH RECOGNITION WITH SPARSE POINT PROCESS MODELS
         Aren Jansen; Johns Hopkins University
         Partha Niyogi; University of Chicago
 
SP-L8.5: TOWARDS MULTI-SPEAKER UNSUPERVISED SPEECH PATTERN DISCOVERY
         Yaodong Zhang; Massachusetts Institute of Technology
         James Glass; Massachusetts Institute of Technology
 
SP-L8.6: BAYESIAN COMPRESSIVE SENSING FOR PHONETIC CLASSIFICATION
         Tara Sainath; IBM T. J. Watson Research Center
         Avishy Carmi; University of Cambridge
         Dimitri Kanevsky; IBM T. J. Watson Research Center
         Bhuvana Ramabhadran; IBM T. J. Watson Research Center
 

©2015 Conference Management Services, Inc. »« email: webmaster@icassp2010.com »« Last updated Tuesday, January 12, 2010