Technical Program
SP-P4: Neural Networks in Speech Recognition |
| Session Type: Poster |
| Time: Tuesday, March 22, 16:00 - 18:00 |
| Location: Poster Area I |
| Session Chair: Xiaodong Cui, IBM Watson |
| SP-P4.1: FLAT START TRAINING OF CD-CTC-SMBR LSTM RNN ACOUSTIC MODELS |
| Kanishka Rao; Google Inc. |
| Andrew Senior; Google Inc. |
| Hasim Sak; Google Inc. |
| SP-P4.2: MULTILINGUAL DATA SELECTION FOR TRAINING STACKED BOTTLENECK FEATURES |
| Ekapol Chuangsuwanich; Massachusetts Institute of Technology |
| Yu Zhang; Massachusetts Institute of Technology |
| James Glass; Massachusetts Institute of Technology |
| SP-P4.3: PREDICTION-ADAPTATION-CORRECTION RECURRENT NEURAL NETWORKS FOR LOW-RESOURCE LANGUAGE SPEECH RECOGNITION |
| Yu Zhang; Massachusetts Institute of Technology |
| Ekapol Chuangsuwanich; Massachusetts Institute of Technology |
| James Glass; Massachusetts Institute of Technology |
| Dong Yu; Microsoft Research |
| SP-P4.4: A STUDY OF RANK-CONSTRAINED MULTILINGUAL DNNS FOR LOW-RESOURCE ASR |
| Reza Sahraeian; Katholieke Universiteit Leuven |
| Dirk Van Compernolle; Katholieke Universiteit Leuven |
| SP-P4.5: SEQUENCE TRAINING OF MULTI-TASK ACOUSTIC MODELS USING META-STATE LABELS |
| Olivier Siohan; Google Inc. |
| SP-P4.6: MULTILINGUAL REGION-DEPENDENT TRANSFORMS |
| Martin Karafiat; BUT |
| Lukas Burget; BUT |
| Frantisek Grezl; BUT |
| Karel Vesely; BUT |
| Jan Cernocky; BUT |
| SP-P4.7: DIVERGENCE ESTIMATION BASED ON DEEP NEURAL NETWORKS AND ITS USE FOR LANGUAGE IDENTIFICATION |
| Yosuke Kashiwagi; The University of Tokyo |
| Congying Zhang; The University of Tokyo |
| Daisuke Saito; The University of Tokyo |
| Nobuaki Minematsu; The University of Tokyo |
| SP-P4.8: EFFECTIVE UTILIZATION OF MULTIPLE EXAMPLES IN QUERY-BY-EXAMPLE SPOKEN TERM DETECTION |
| Ji Xu; The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences |
| Ge Zhang; The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences |
| Yonghong Yan; The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences |
| SP-P4.9: EXPLOITING LSTM STRUCTURE IN DEEP NEURAL NETWORKS FOR SPEECH RECOGNITION |
| Tianxing He; Shanghai Jiao Tong University |
| Jasha Droppo; Microsoft Corporation |
| SP-P4.10: SELF-STABILIZED DEEP NEURAL NETWORK |
| Pegah Ghahremani; Johns Hopkins University |
| Jasha Droppo; Microsoft Research |
ICASSP 2016 Patrons
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |