2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
SPE-2: Speech Recognition 2: Neural transducer Models 2 |
| Session Type: Poster |
| Time: Tuesday, 8 June, 13:00 - 13:45 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Tara Sainath, Google Inc. |
| SPE-2.1: ADVANCING RNN TRANSDUCER TECHNOLOGY FOR SPEECH RECOGNITION |
| George Saon; IBM Research AI |
| Zoltan Tueske; IBM Research AI |
| Daniel Bolanos; IBM Research AI |
| Brian Kingsbury; IBM Research AI |
| SPE-2.2: LESS IS MORE: IMPROVED RNN-T DECODING USING LIMITED LABEL CONTEXT AND PATH MERGING |
| Rohit Prabhavalkar; Google |
| Yanzhang He; Google |
| David Rybach; Google |
| Sean Campbell; Google |
| Arun Narayanan; Google |
| Trevor Strohman; Google |
| Tara N. Sainath; Google |
| SPE-2.3: SIMPLEFLAT: A SIMPLE WHOLE-NETWORK PRE-TRAINING APPROACH FOR RNN TRANSDUCER-BASED END-TO-END SPEECH RECOGNITION |
| Takafumi Moriya; NTT Corporation |
| Takanori Ashihara; NTT Corporation |
| Tomohiro Tanaka; NTT Corporation |
| Tsubasa Ochiai; NTT Corporation |
| Hiroshi Sato; NTT Corporation |
| Atsushi Ando; NTT Corporation |
| Yusuke Ijima; NTT Corporation |
| Ryo Masumura; NTT Corporation |
| Yusuke Shinohara; NTT Corporation |
| SPE-2.4: ECHO STATE SPEECH RECOGNITION |
| Harsh Shrivastava; Georgia Institute of Technology |
| Ankush Garg; Google |
| Yuan Cao; Google |
| Yu Zhang; Google |
| Tara N. Sainath; Google |
| SPE-2.5: USING SYNTHETIC AUDIO TO IMPROVE THE RECOGNITION OF OUT-OF-VOCABULARY WORDS IN END-TO-END ASR SYSTEMS |
| Xianrui Zheng; University of Cambridge |
| Yulan Liu; Amazon |
| Deniz Gunceler; Amazon |
| Daniel Willett; Amazon |