Technical Program
SP-L3: Acoustic Model Adaptation for Speech Recognition II |
| Session Type: Lecture |
| Time: Wednesday, March 23, 08:30 - 10:30 |
| Location: Yangtse River Hall (5F) |
| Session Chairs: John Hansen, University of Texas at Dallas and Kai Yu, Shanghai Jiao Tong University |
| SP-L3.1: COMBINING I-VECTOR REPRESENTATION AND STRUCTURED NEURAL NETWORKS FOR RAPID ADAPTATION |
| Chunyang Wu; University of Cambridge |
| Penny Karanasou; University of Cambridge |
| Mark Gales; University of Cambridge |
| SP-L3.2: LOW-RANK PLUS DIAGONAL ADAPTATION FOR DEEP NEURAL NETWORKS |
| Yong Zhao; Microsoft Corporation |
| Jinyu Li; Microsoft Corporation |
| Yifan Gong; Microsoft Corporation |
| SP-L3.3: SAT-LHUC: SPEAKER ADAPTIVE TRAINING FOR LEARNING HIDDEN UNIT CONTRIBUTIONS |
| Pawel Swietojanski; University of Edinburgh |
| Steve Renals; University of Edinburgh |
| SP-L3.4: BOTTLENECK LINEAR TRANSFORMATION NETWORK ADAPTATION FOR SPEAKER ADAPTIVE TRAINING-BASED HYBRID DNN-HMM SPEECH RECOGNIZER |
| Tsubasa Ochiai; NICT/Doshisha University |
| Shigeki Matsuda; Doshisha University |
| Hideyuki Watanabe; NICT |
| Xugang Lu; NICT |
| Hisashi Kawai; NICT |
| Shigeru Katagiri; Doshisha University |
| SP-L3.5: INVESTIGATIONS ON SPEAKER ADAPTATION OF LSTM RNN MODELS FOR SPEECH RECOGNITION |
| Chaojun Liu; Microsoft Corporation |
| Yongqiang Wang; Microsoft Corporation |
| Kshitiz Kumar; Microsoft Corporation |
| Yifan Gong; Microsoft Corporation |
| SP-L3.6: JOINT ACOUSTIC FACTOR LEARNING FOR ROBUST DEEP NEURAL NETWORK BASED AUTOMATIC SPEECH RECOGNITION |
| Souvik Kundu; National University of Singapore |
| Gautam Mantena; National University of Singapore |
| Yanmin Qian; Shanghai Jiao Tong University |
| Tian Tan; Shanghai Jiao Tong University |
| Marc Delcroix; Nippon Telegraph and Telephone Corporation |
| Khe Chai Sim; National University of Singapore |
ICASSP 2016 Patrons
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |