ESPnet-ST IWSLT 2021 Offline Speech Translation System

Hirofumi Inaguma, Brian Yan, Siddharth Dalmia, Pengcheng Guo, Jiatong Shi, Kevin Duh, Shinji Watanabe


Abstract
This paper describes the ESPnet-ST group’s IWSLT 2021 submission in the offline speech translation track. This year we made various efforts on training data, architecture, and audio segmentation. On the data side, we investigated sequence-level knowledge distillation (SeqKD) for end-to-end (E2E) speech translation. Specifically, we used multi-referenced SeqKD from multiple teachers trained on different amounts of bitext. On the architecture side, we adopted the Conformer encoder and the Multi-Decoder architecture, which equips dedicated decoders for speech recognition and translation tasks in a unified encoder-decoder model and enables search in both source and target language spaces during inference. We also significantly improved audio segmentation by using the pyannote.audio toolkit and merging multiple short segments for long context modeling. Experimental evaluations showed that each of them contributed to large improvements in translation performance. Our best E2E system combined all the above techniques with model ensembling and achieved 31.4 BLEU on the 2-ref of tst2021 and 21.2 BLEU and 19.3 BLEU on the two single references of tst2021.
Anthology ID:
2021.iwslt-1.10
Volume:
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
Month:
August
Year:
2021
Address:
Bangkok, Thailand (online)
Editors:
Marcello Federico, Alex Waibel, Marta R. Costa-jussà, Jan Niehues, Sebastian Stuker, Elizabeth Salesky
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
100–109
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.iwslt-1.10/
DOI:
10.18653/v1/2021.iwslt-1.10
Bibkey:
Cite (ACL):
Hirofumi Inaguma, Brian Yan, Siddharth Dalmia, Pengcheng Guo, Jiatong Shi, Kevin Duh, and Shinji Watanabe. 2021. ESPnet-ST IWSLT 2021 Offline Speech Translation System. In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), pages 100–109, Bangkok, Thailand (online). Association for Computational Linguistics.
Cite (Informal):
ESPnet-ST IWSLT 2021 Offline Speech Translation System (Inaguma et al., IWSLT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.iwslt-1.10.pdf
Data
LibriSpeechMuST-CTED-LIUM