Technical Program

SP-L5: Acoustic Modeling for Speech Recognition

Session Type: Lecture
Time: Wednesday, March 23, 16:00 - 18:00
Location: Room 3E
Session Chairs: Geoffrey Zweig, Microsoft Research and Shinji Watanabe, Mitsubishi Electric Research Labs
 
SP-L5.1: ON TRAINING THE RECURRENT NEURAL NETWORK ENCODER-DECODER FOR LARGE VOCABULARY END-TO-END SPEECH RECOGNITION
         Liang Lu; The University of Edinburgh
         Xingxing Zhang; The University of Edinburgh
         Steve Renals; The University of Edinburgh
 
SP-L5.2: DISCRIMINATIVELY TRAINED JOINT SPEAKER AND ENVIRONMENT REPRESENTATIONS FOR ADAPTATION OF DEEP NEURAL NETWORK ACOUSTIC MODELS
         Maofan Yin; Shanghai Jiao Tong University
         Sunil Sivadas; Institute for Infocomm Research
         Kai Yu; Shanghai Jiao Tong University
         Bin Ma; Institute for Infocomm Research
 
SP-L5.3: A COMPARISON BETWEEN DEEP NEURAL NETS AND KERNEL ACOUSTIC MODELS FOR SPEECH RECOGNITION
         Zhiyun Lu; University of California, Los Angeles
         Dong Guo; University of Southern California
         Alireza Bagheri Garakani; University of Southern California
         Kuan Liu; University of Southern California
         Avner May; Columbia University
         Aurelien Bellet; Team Magnet, INRIA Lille - Nord Europe
         Linxi Fan; Columbia University
         Michael Collins; Columbia University
         Brian Kingsbury; IBM
         Michael Picheny; IBM
         Fei Sha; University of California, Los Angeles
 
SP-L5.4: FACTORED SPATIAL AND SPECTRAL MULTICHANNEL RAW WAVEFORM CLDNNS
         Tara Sainath; Google Inc.
         Ron Weiss; Google Inc.
         Kevin Wilson; Google Inc.
         Arun Narayanan; Google Inc.
         Michiel Bacchiani; Google Inc.
 
SP-L5.5: HOW NEURAL NETWORK FEATURES AND DEPTH MODIFY STATISTICAL PROPERTIES OF HMM ACOUSTIC MODELS
         Suman Ravuri; International Computer Science Institute; University of California - Berkeley
         Steven Wegmann; International Computer Science Institute/Semantic Machines
 
SP-L5.6: LINEARLY AUGMENTED DEEP NEURAL NETWORK
         Pegah Ghahremani; Johns Hopkins University
         Jasha Droppo; Microsoft Research
         Michael L. Seltzer; Microsoft Research
 

ICASSP 2016 Patrons