Technical Program
SP-L8: Acoustic Modeling and Adaptation |
| Session Type: Lecture |
| Time: Wednesday, March 8, 16:00 - 18:00 |
| Location: Grand Salon 16 |
| Session Chairs: Michiel Bacchiani, Google and Koichi Shinoda, Tokyo Institute of Technology |
| SP-L8.1: JOINT OPTIMISATION OF TANDEM SYSTEMS USING GAUSSIAN MIXTURE DENSITY NEURAL NETWORK DISCRIMINATIVE SEQUENCE TRAINING |
| Chao Zhang; Cambridge University |
| Phil Woodland; Cambridge University |
| SP-L8.2: VISUAL FEATURES FOR CONTEXT-AWARE SPEECH RECOGNITION |
| Abhinav Gupta; Carnegie Mellon University |
| Yajie Miao; Carnegie Mellon University |
| Leonardo Neves; Carnegie Mellon University |
| Florian Metze; Carnegie Mellon University |
| SP-L8.3: EXPLOITING SEQUENTIAL LOW-RANK FACTORIZATION FOR MULTILINGUAL DNNS |
| Reza Sahraeian; KU Leuven |
| Dirk Van Compernolle; KU Leuven |
| SP-L8.4: LOW-RESOURCE GRAPHEME-TO-PHONEME CONVERSION USING RECURRENT NEURAL NETWORKS |
| Preethi Jyothi; Indian Institute of Technology Bombay |
| Mark Hasegawa-Johnson; University of Illinois at Urbana-Champaign |
| SP-L8.5: AN INVESTIGATION INTO LEARNING EFFECTIVE SPEAKER SUBSPACES FOR ROBUST UNSUPERVISED DNN ADAPTATION |
| Lahiru Samarakoon; National University of Singapore |
| Khe Chai Sim; Google Inc. |
| Brian Mak; Hong Kong University of Science and Technology |
| SP-L8.6: EXTENDED LOW-RANK PLUS DIAGONAL ADAPTATION FOR DEEP AND RECURRENT NEURAL NETWORKS |
| Yong Zhao; Microsoft |
| Jinyu Li; Microsoft |
| Kshitiz Kumar; Microsoft |
| Yifan Gong; Microsoft |