ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020

Maha Elbayad, Ha Nguyen, Fethi Bougares, Natalia Tomashenko, Antoine Caubrière, Benjamin Lecouteux, Yannick Estève, Laurent Besacier


Abstract
This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2020, offline speech translation and simultaneous speech translation. ON-TRAC Consortium is composed of researchers from three French academic laboratories: LIA (Avignon Université), LIG (Université Grenoble Alpes), and LIUM (Le Mans Université). Attention-based encoder-decoder models, trained end-to-end, were used for our submissions to the offline speech translation track. Our contributions focused on data augmentation and ensembling of multiple models. In the simultaneous speech translation track, we build on Transformer-based wait-k models for the text-to-text subtask. For speech-to-text simultaneous translation, we attach a wait-k MT system to a hybrid ASR system. We propose an algorithm to control the latency of the ASR+MT cascade and achieve a good latency-quality trade-off on both subtasks.
Anthology ID:
2020.iwslt-1.2
Volume:
Proceedings of the 17th International Conference on Spoken Language Translation
Month:
July
Year:
2020
Address:
Online
Editors:
Marcello Federico, Alex Waibel, Kevin Knight, Satoshi Nakamura, Hermann Ney, Jan Niehues, Sebastian Stüker, Dekai Wu, Joseph Mariani, Francois Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
35–43
Language:
URL:
https://aclanthology.org/2020.iwslt-1.2
DOI:
10.18653/v1/2020.iwslt-1.2
Bibkey:
Cite (ACL):
Maha Elbayad, Ha Nguyen, Fethi Bougares, Natalia Tomashenko, Antoine Caubrière, Benjamin Lecouteux, Yannick Estève, and Laurent Besacier. 2020. ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 35–43, Online. Association for Computational Linguistics.
Cite (Informal):
ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020 (Elbayad et al., IWSLT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwslt-1.2.pdf
Video:
 http://slideslive.com/38929610
Data
How2MuST-C