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 |