Technical Program

SP-P14: Speech Recognition III

Session Type: Poster
Time: Friday, March 25, 13:30 - 15:30
Location: Poster Area H
Session Chair: Hakan Erdogan, Sabanci University
 
SP-P14.1: COMPARISON OF UNSUPERVISED SEQUENCE ADAPTATIONS FOR DEEP NEURAL NETWORKS
         Akio Kobayashi; NHK Engineering System
         Kazuo Onoe; NHK Science and Technology Research Laboratories
         Manon Ichiki; NHK Science and Technology Research Laboratories
         Shoei Sato; NHK Science and Technology Research Laboratories
 
SP-P14.2: SYNAPTIC DEPRESSION IN DEEP NEURAL NETWORKS FOR SPEECH PROCESSING
         Wenhao Zhang; Columbia University
         Hanyu Li; Columbia University
         Minda Yang; Columbia University
         Nima Mesgarani; Columbia University
 
SP-P14.3: GEO-LOCATION DEPENDENT DEEP NEURAL NETWORK ACOUSTIC MODEL FOR SPEECH RECOGNITION
         Guoli Ye; Microsoft Search Technology Center Asia
         Chaojun Liu; Microsoft Corporation
         Yifan Gong; Microsoft Corporation
 
SP-P14.4: DATA SELECTION FROM MULTIPLE ASR SYSTEMS' HYPOTHESES FOR UNSUPERVISED ACOUSTIC MODEL TRAINING
         Sheng Li; Kyoto University
         Yuya Akita; Kyoto University
         Tatsuya Kawahara; Kyoto University
 
SP-P14.5: SCALABLE TRAINING OF DEEP LEARNING MACHINES BY INCREMENTAL BLOCK TRAINING WITH INTRA-BLOCK PARALLEL OPTIMIZATION AND BLOCKWISE MODEL-UPDATE FILTERING
         Kai Chen; University of Science and Technology of China
         Qiang Huo; Microsoft Research Asia
 
SP-P14.6: RECURRENT SUPPORT VECTOR MACHINES FOR SPEECH RECOGNITION
         Shi-Xiong Zhang; Microsoft Corporation
         Rui Zhao; Microsoft Corporation
         Chaojun Liu; Microsoft Corporation
         Jinyu Li; Microsoft Corporation
         Yifan Gong; Microsoft Corporation
 
SP-P14.7: PROBABILISTIC CLASS HISTOGRAM EQUALIZATION BASED ON POSTERIOR MEAN ESTIMATION FOR ROBUST SPEECH RECOGNITION
         Youngjoo Suh; Korea Advanced Institute of Science and Technology
         Hoirin Kim; Korea Advanced Institute of Science and Technology
 
SP-P14.8: ROBUST SPEECH RECOGNITION USING MULTIVARIATE COPULA MODELS
         Alireza Bayestehtashk; Oregon Health & Science University
         Izhak Shafran; Google Inc.
         Amir Babaeian; University of California, San Diego
 
SP-P14.9: FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION
         Hardik Sailor; Dhirubhai Ambani Institute of Information and Communication Technology
         Hemant Patil; Dhirubhai Ambani Institute of Information and Communication Technology
 
SP-P14.10: RECURRENT NEURAL NETWORK TRAINING WITH DARK KNOWLEDGE TRANSFER
         Zhiyuan Tang; Tsinghua University
         Dong Wang; Tsinghua University
         Zhiyong Zhang; Tsinghua University
 

ICASSP 2016 Patrons