Technical Program

SP-L1: Automatic Speech Recognition using Neural Networks

Session Type: Lecture
Time: Tuesday, May 28, 10:50 - 12:50
Location: Room 211
Session Chair: Bhuvana Ramabhadran, IBM T. J. Watson Research Center
 
SP-L1.1: SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS
         Alex Graves; University of Toronto
         Abdel-Rahman Mohamed; University of Toronto
         Geoffrey E. Hinton; University of Toronto
 
SP-L1.2: A CLUSTER-BASED MULTIPLE DEEP NEURAL NETWORKS METHOD FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
         Pan Zhou; University of Science and Technology of China
         Cong Liu; Anhui USTC iFLYTEK Corporation Limited
         Qingfeng Liu; Anhui USTC iFLYTEK Corporation Limited
         Li-Rong Dai; University of Science and Technology of China
         Hui Jiang; York University
 
SP-L1.3: LOW-RANK MATRIX FACTORIZATION FOR DEEP NEURAL NETWORK TRAINING WITH HIGH-DIMENSIONAL OUTPUT TARGETS
         Tara N. Sainath; IBM T.J. Watson Research Center
         Brian Kingsbury; IBM T.J. Watson Research Center
         Vikas Sindhwani; IBM T.J. Watson Research Center
         Ebru Arisoy; IBM T.J. Watson Research Center
         Bhuvana Ramabhadran; IBM T.J. Watson Research Center
 
SP-L1.4: ASYNCHRONOUS STOCHASTIC GRADIENT DESCENT FOR DNN TRAINING
         Shanshan Zhang; Institute of Automation, Chinese Academy of Sciences
         Ce Zhang; Institute of Automation, Chinese Academy of Sciences
         Zhao You; Institute of Automation, Chinese Academy of Sciences
         Rong Zheng; Institute of Automation, Chinese Academy of Sciences
         Bo Xu; Institute of Automation, Chinese Academy of Sciences
 
SP-L1.5: ERROR BACK PROPAGATION FOR SEQUENCE TRAINING OF CONTEXT-DEPENDENT DEEP NETWORKS FOR CONVERSATIONAL SPEECH TRANSCRIPTION
         Hang Su; Tsinghua University
         Gang Li; Microsoft Corporation
         Dong Yu; Microsoft Corporation
         Frank Seide; Microsoft Corporation
 
SP-L1.6: A DEEP CONVOLUTIONAL NEURAL NETWORK USING HETEROGENEOUS POOLING FOR TRADING ACOUSTIC INVARIANCE WITH PHONETIC CONFUSION
         Li Deng; Microsoft Research
         Ossama Abdel-Hamid; York University
         Dong Yu; Microsoft Corporation