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 |