ASR III (End-to-End) |
| Session Type: Poster |
| Time: Friday, December 21, 10:00 - 12:00 |
| Location: Kallirhoe Hall |
| IMPROVING ATTENTION-BASED END-TO-END ASR SYSTEMS WITH SEQUENCE-BASED LOSS FUNCTIONS |
| Jia Cui; Tencent AI Lab |
| Chao Weng; Tencent AI Lab |
| Guangsen Wang; Tencent AI Lab |
| Jun Wang; Tencent AI Lab |
| Peidong Wang; The Ohio State University |
| Chengzhu Yu; Tencent AI Lab |
| Dan Su; Tencent AI Lab |
| Dong Yu; Tencent AI Lab |
| COMBINING END-TO-END AND ADVERSARIAL TRAINING FOR LOW-RESOURCE SPEECH RECOGNITION |
| Jennifer Drexler; Massachusetts Institute of Technology |
| James Glass; Massachusetts Institute of Technology |
| A COMPARISON OF TECHNIQUES FOR LANGUAGE MODEL INTEGRATION IN ENCODER-DECODER SPEECH RECOGNITION |
| Shubham Toshniwal; Toyota Technological Institute at Chicago |
| Anjuli Kannan; Google |
| Chung-Cheng Chiu; Google |
| Yonghui Wu; Google |
| Tara N. Sainath; Google |
| Karen Livescu; Toyota Technological Institute at Chicago |
| ON-DEVICE END-TO-END SPEECH RECOGNITION WITH MULTI-STEP PARALLEL RNNS |
| Yoonho Boo; Seoul National University |
| Jinhwan Park; Seoul National University |
| Lukas Lee; Seoul National University |
| Wonyong Sung; Seoul National University |
| DOMAIN ADAPTATION OF END-TO-END SPEECH RECOGNITION IN LOW-RESOURCE SETTINGS |
| Lahiru Samarakoon; Fano Labs |
| Brian Mak; Hong Kong University of Science and Technology |
| Albert Lam; Fano Labs |
| END-TO-END SPEECH RECOGNITION WITH WORD-BASED RNN LANGUAGE MODELS |
| Takaaki Hori; Mitsubishi Electric Research Laboratories |
| Jaejin Cho; Johns Hopkins University |
| Shinji Watanabe; Johns Hopkins University |
| ACOUSTIC-TO-WORD RECOGNITION WITH SEQUENCE-TO-SEQUENCE MODELS |
| Shruti Palaskar; Carnegie Mellon University |
| Florian Metze; Carnegie Mellon University |
| COMBINING DE-NOISING AUTO-ENCODER AND RECURRENT NEURAL NETWORKS IN END-TO-END AUTOMATIC SPEECH RECOGNITION FOR NOISE ROBUSTNESS |
| Tzu-Hsuan Ting; National Sun Yat-sen University |
| Chia-Ping Chen; National Sun Yat-sen University |
| IMPROVED KNOWLEDGE DISTILLATION FROM BI-DIRECTIONAL TO UNI-DIRECTIONAL LSTM CTC FOR END-TO-END SPEECH RECOGNITION |
| Gakuto Kurata; IBM Research |
| Kartik Audhkhasi; IBM Research |
| DEEP CONTEXT: END-TO-END CONTEXTUAL SPEECH RECOGNITION |
| Golan Pundak; Google |
| Tara N. Sainath; Google |
| Rohit Prabhavalkar; Google |
| Anjuli Kannan; Google |
| Ding Zhao; Google |
| BACK-TRANSLATION-STYLE DATA AUGMENTATION FOR END-TO-END ASR |
| Tomoki Hayashi; Nagoya University |
| Shinji Watanabe; Johns Hopkins University |
| Yu Zhang; Google |
| Tomoki Toda; Nagoya University |
| Takaaki Hori; Mitsubishi Electric Research Laboratories |
| Ramon Astudillo; INESC-ID-Lisboa |
| Kazuya Takeda; Nagoya University |
| DIALOG-CONTEXT AWARE END-TO-END SPEECH RECOGNITION |
| Suyoun Kim; Carnegie Mellon University |
| Florian Metze; Carnegie Mellon University |