ASR I |
| Session Type: Poster |
| Time: Wednesday, December 19, 10:00 - 12:00 |
| Location: Kallirhoe Hall |
| HIGH-DEGREE FEATURE FOR DEEP NEURAL NETWORK BASED ACOUSTIC MODEL |
| Hoon Chung; Electronics and Telecommunications Research Institute |
| Sung Joo Lee; Electronics and Telecommunications Research Institute |
| Jeon Gue Park; Electronics and Telecommunications Research Institute |
| DENSENET BLSTM FOR ACOUSTIC MODELING IN ROBUST ASR |
| Maximilian Strake; Technische Universität Braunschweig |
| Pascal Behr; Technische Universität Braunschweig |
| Timo Lohrenz; Technische Universität Braunschweig |
| Tim Fingscheidt; Technische Universität Braunschweig |
| PHASE-BASED FEATURE REPRESENTATIONS FOR IMPROVING RECOGNITION OF DYSARTHRIC SPEECH |
| Siddharth Sehgal; University of Sheffield |
| Stuart Cunningham; University of Sheffield |
| Phil Green; University of Sheffield |
| EFFICIENT BUILDING STRATEGY WITH KNOWLEDGE DISTILLATION FOR SMALL-FOOTPRINT ACOUSTIC MODELS |
| Takafumi Moriya; NTT Corporation |
| Hiroki Kanagawa; NTT Corporation |
| Kiyoaki Matsui; NTT Corporation |
| Takaaki Fukutomi; NTT Corporation |
| Yusuke Shinohara; NTT Corporation |
| Yoshikazu Yamaguchi; NTT Corporation |
| Manabu Okamoto; NTT Corporation |
| Yushi Aono; NTT Corporation |
| ADVANCING MULTI-ACCENTED LSTM-CTC SPEECH RECOGNITION USING A DOMAIN SPECIFIC STUDENT-TEACHER LEARNING PARADIGM |
| Shahram Ghorbani; University of Texas at Dallas |
| Ahmet E. Bulut; University of Texas at Dallas |
| John H.L. Hansen; University of Texas at Dallas |
| DYNAMIC EXTENSION OF ASR LEXICON USING WIKIPEDIA DATA |
| Badr Abdullah; LORIA/INRIA |
| Irina Illina; LORIA/INRIA |
| Dominique Fohr; LORIA/INRIA |
| IMPROVING LF-MMI USING UNCONSTRAINED SUPERVISIONS FOR ASR |
| Hossein Hadian; Sharif University of Technology |
| Daniel Povey; Johns Hopkins University |
| Hossein Sameti; Sharif University of Technology |
| Jan Trmal; Johns Hopkins University |
| Sanjeev Khudanpur; Johns Hopkins University |
| ON TRAINING RECURRENT NETWORKS WITH TRUNCATED BACKPROPAGATION THROUGH TIME IN SPEECH RECOGNITION |
| Hao Tang; Massachusetts Institute of Technology |
| James Glass; Massachusetts Institute of Technology |
| LEARNING NOISE-INVARIANT REPRESENTATIONS FOR ROBUST SPEECH RECOGNITION |
| Davis Liang; Amazon AI |
| Zhiheng Huang; Amazon AI |
| Zachary Lipton; Carnegie Mellon University |
| AN EXPLORATION OF DIRECTLY USING WORD AS ACOUSTIC MODELING UNIT FOR SPEECH RECOGNITION |
| Chunlei Zhang; The University of Texas at Dallas |
| Chengzhu Yu; Tencent AI Lab |
| Chao Weng; Tencent AI Lab |
| Jia Cui; Tencent AI Lab |
| Dong Yu; Tencent AI Lab |
| IMPROVED TRAINING OF NEURAL TRANS-DIMENSIONAL RANDOM FIELD LANGUAGE MODELS WITH DYNAMIC NOISE-CONTRASTIVE ESTIMATION |
| Bin Wang; Tsinghua University |
| Zhijian Ou; Tsinghua University |
| IMPROVING VERY DEEP TIME-DELAY NEURAL NETWORK WITH VERTICAL-ATTENTION FOR EFFECTIVELY TRAINING CTC-BASED ASR SYSTEMS |
| Sheng Li; National Institute of Information and Communications Technology |
| Xugang Lu; National Institute of Information and Communications Technology |
| Ryoichi Takashima; National Institute of Information and Communications Technology |
| Peng Shen; National Institute of Information and Communications Technology |
| Tatsuya Kawahara; National Institute of Information and Communications Technology (NICT) / Kyoto University |
| Hisashi Kawai; National Institute of Information and Communications Technology |