Technical Program
SP-P11: Acoustic Modeling: Novel Methods for Automatic Speech Recognition |
| Session Type: Poster |
| Time: Wednesday, May 29, 15:20 - 17:20 |
| Location: Poster Area D |
| Session Chair: Hermann Ney, RWTH-Aachen |
| SP-P11.1: MULTIFRAME DEEP NEURAL NETWORKS FOR ACOUSTIC MODELING |
| Vincent Vanhoucke; Google Inc. |
| Matthieu Devin; Google Inc. |
| Georg Heigold; Google Inc. |
| SP-P11.2: INVESTIGATION OF TANDEM DEEP BELIEF NETWORK APPROACH FOR PHONEME RECOGNITION |
| Xin Zheng; Tsinghua University |
| Zhiyong Wu; Tsinghua University |
| Binbin Shen; Tsinghua University |
| Helen Meng; The Chinese University of Hong Kong |
| Lianhong Cai; Tsinghua University |
| SP-P11.3: USING MULTIPLE VERSIONS OF SPEECH INPUT IN PHONE RECOGNITION |
| Mark Liberman; University of Pennsylvania |
| Jiahong Yuan; University of Pennsylvania |
| Andreas Stolcke; Microsoft Research |
| Wen Wang; SRI International |
| Vikramjit Mitra; SRI International |
| SP-P11.4: AUDIO-VISUAL DEEP LEARNING FOR NOISE ROBUST SPEECH RECOGNITION |
| Jing Huang; IBM |
| Brian Kingsbury; IBM |
| SP-P11.5: INVESTIGATION OF DEEP BOLTZMANN MACHINES FOR PHONE RECOGNITION |
| Zhao You; Institute of Automation, Chinese Academy of Sciences |
| Xiaorui Wang; Institute of Automation, Chinese Academy of Sciences |
| Bo Xu; Institute of Automation, Chinese Academy of Sciences |
| SP-P11.6: FEATURE AND SCORE LEVEL COMBINATION OF SUBSPACE GAUSSINAS IN LVCSR TASK |
| Petr Motlicek; Idiap Research Institute |
| Daniel Povey; Johns Hopkins University |
| Martin Karafiat; Brno University of Technology |
| SP-P11.7: UPPER AND LOWER BOUNDS FOR APPROXIMATION OF THE KULLBACK-LEIBLER DIVERGENCE BETWEEN HIDDEN MARKOV MODELS |
| Haiyang Li; Harbin Institute of Technology |
| Jiqing Han; Harbin Institute of Technology |
| Tieran Zheng; Harbin Institute of Technology |
| Guibin Zheng; Harbin Institute of Technology |
| SP-P11.8: UNDERSTANDING THE DROPOUT STRATEGY AND ANALYZING ITS EFFECTIVENESS ON LVCSR |
| Jie Li; Institute of Automation, Chinese Academy of Sciences |
| Xiaorui Wang; Institute of Automation, Chinese Academy of Sciences |
| Bo Xu; Institute of Automation, Chinese Academy of Sciences |
| SP-P11.9: EFFICIENT DECODING WITH GENERATIVE SCORE-SPACES USING THE EXPECTATION SEMIRING |
| Rogier van Dalen; University of Cambridge |
| Anton Ragni; University of Cambridge |
| Mark J.F. Gales; University of Cambridge |
| SP-P11.10: IDENTIFICATION AND MODELING OF WORD FRAGMENTS IN SPONTANEOUS SPEECH |
| Yulia Tsvetkov; Carnegie Mellon University |
| Zaid Sheikh; Carnegie Mellon University |
| Florian Metze; Carnegie Mellon University |
| SP-P11.11: LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION BASED ON WFST STRUCTURED CLASSIFIERS AND DEEP BOTTLENECK FEATURES |
| Yotaro Kubo; Nippon Telegraph and Telephone Corporation |
| Takaaki Hori; Nippon Telegraph and Telephone Corporation |
| Atsushi Nakamura; Nippon Telegraph and Telephone Corporation |
| SP-P11.12: DEEP NEURAL NETWORKS WITH AUXILIARY GAUSSIAN MIXTURE MODELS FOR REAL-TIME SPEECH RECOGNITION |
| Xin Lei; Google Inc. |
| Hui Lin; Google Inc. |
| Georg Heigold; Google Inc. |