2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
SPE-32: Speech Recognition 12: Self-supervised, Semi-supervised, Unsupervised Training |
| Session Type: Poster |
| Time: Thursday, 10 June, 13:00 - 13:45 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Jinyu Li, Microsoft |
| SPE-32.1: HUBERT: HOW MUCH CAN A BAD TEACHER BENEFIT ASR PRE-TRAINING? |
| Wei-Ning Hsu; Facebook AI Research |
| Yao-Hung Hubert Tsai; Carnegie Mellon University |
| Benjamin Bolte; Facebook AI Research |
| Ruslan Salakhutdinov; Carnegie Mellon University |
| Abdelrahman Mohamed; Facebook AI Research |
| SPE-32.2: A FURTHER STUDY OF UNSUPERVISED PRETRAINING FOR TRANSFORMER BASED SPEECH RECOGNITION |
| Dongwei Jiang; Didi Chuxing |
| Wubo Li; Didi Chuxing |
| Ruixiong Zhang; Didi Chuxing |
| Miao Cao; Didi Chuxing |
| Ne Luo; Didi Chuxing |
| Yang Han; Didi Chuxing |
| Wei Zou; Didi Chuxing |
| Kun Han; Didi Chuxing |
| Xiangang Li; Didi Chuxing |
| SPE-32.3: PRE-TRAINING TRANSFORMER DECODER FOR END-TO-END ASR MODEL WITH UNPAIRED TEXT DATA |
| Changfeng Gao; Key Laboratory of Speech Acoustics and Content Understanding |
| Gaofeng Cheng; Key Laboratory of Speech Acoustics and Content Understanding |
| Runyan Yang; Key Laboratory of Speech Acoustics and Content Understanding |
| Han Zhu; Key Laboratory of Speech Acoustics and Content Understanding |
| Pengyuan Zhang; Key Laboratory of Speech Acoustics and Content Understanding |
| Yonghong Yan; Key Laboratory of Speech Acoustics and Content Understanding |
| SPE-32.4: SEMI-SUPERVISED SPEECH RECOGNITION VIA GRAPH-BASED TEMPORAL CLASSIFICATION |
| Niko Moritz; Mitsubishi Electric Research Laboratories (MERL) |
| Takaaki Hori; Mitsubishi Electric Research Laboratories (MERL) |
| Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL) |
| SPE-32.5: UNSUPERVISED DOMAIN ADAPTATION FOR SPEECH RECOGNITION VIA UNCERTAINTY DRIVEN SELF-TRAINING |
| Sameer Khurana; Massachusetts Institute of Technology |
| Niko Moritz; Mitsubishi Electric Research Laboratories (MERL) |
| Takaaki Hori; Mitsubishi Electric Research Laboratories (MERL) |
| Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL) |
| SPE-32.6: IMPROVING STREAMING AUTOMATIC SPEECH RECOGNITION WITH NON-STREAMING MODEL DISTILLATION ON UNSUPERVISED DATA |
| Thibault Doutre; Google Inc. |
| Wei Han; Google Inc. |
| Min Ma; Google Inc. |
| Zhiyun Lu; Google Inc. |
| Chung-Cheng Chiu; Google Inc. |
| Ruoming Pang; Google Inc. |
| Arun Narayanan; Google Inc. |
| Ananya Misra; Google Inc. |
| Yu Zhang; Google Inc. |
| Liangliang Cao; Google Inc. |