Title | ||
---|---|---|
An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition |
Abstract | ||
---|---|---|
Self-supervised pretraining on speech data has achieved a lot of progress. High-fidelity representation of the speech signal is learned from a lot of untranscribed data and shows promising performance. Recently, there are several works focusing on evaluating the quality of self-supervised pretrained representations on various tasks with-out domain restriction, e.g. SUPERB. However, such evaluations do not provide a comprehensive comparison among many ASR benchmark corpora. In this paper, we focus on the general applications of pretrained speech representations, on advanced end-to-end automatic speech recognition (E2E-ASR) models. We select sev-eral pretrained speech representations and present the experimental results on various open-source and publicly available corpora for E2E-ASR. Without any modification of the back-end model archi-tectures or training strategy, some of the experiments with pretrained representations, e.g., WSJ, WSJ0-2mix with HuBERT, reach or out-perform current state-of-the-art (SOTA) recognition performance. Moreover, we further explore more scenarios for whether the pre-training representations are effective, such as the cross-language or overlapped speech. The scripts, configuratons and the trained mod-els have been released in ESPnet to let the community reproduce our experiments and improve them. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ASRU51503.2021.9688137 | 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) |
Keywords | DocType | ISBN |
Representation Learning,End-to-End Speech Recognition,ESPnet | Conference | 978-1-6654-3740-0 |
Citations | PageRank | References |
2 | 0.36 | 0 |
Authors | ||
11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xuankai Chang | 1 | 2 | 0.70 |
Takashi Maekaku | 2 | 2 | 0.36 |
Pengcheng Guo | 3 | 2 | 0.36 |
Jing Shi | 4 | 2 | 0.36 |
Yen-Ju Lu | 5 | 2 | 0.36 |
S. Aswin Shanmugam | 6 | 7 | 4.21 |
Tianzi Wang | 7 | 3 | 0.71 |
Shu-wen Yang | 8 | 17 | 1.38 |
Yu Tsao | 9 | 208 | 50.09 |
Hung-Yi Lee | 10 | 217 | 45.30 |
Shinji Watanabe | 11 | 1158 | 139.38 |