DiDi Labs’ End-to-end System for the IWSLT 2020 Offline Speech TranslationTask

Arkady Arkhangorodsky, Yiqi Huang, Amittai Axelrod


Abstract
This paper describes the system that was submitted by DiDi Labs to the offline speech translation task for IWSLT 2020. We trained an end-to-end system that translates audio from English TED talks to German text, without producing intermediate English text. We use the S-Transformer architecture and train using the MuSTC dataset. We also describe several additional experiments that were attempted, but did not yield improved results.
Anthology ID:
2020.iwslt-1.6
Volume:
Proceedings of the 17th International Conference on Spoken Language Translation
Month:
July
Year:
2020
Address:
Online
Venues:
ACL | IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
69–72
Language:
URL:
https://aclanthology.org/2020.iwslt-1.6
DOI:
10.18653/v1/2020.iwslt-1.6
Bibkey:
Cite (ACL):
Arkady Arkhangorodsky, Yiqi Huang, and Amittai Axelrod. 2020. DiDi Labs’ End-to-end System for the IWSLT 2020 Offline Speech TranslationTask. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 69–72, Online. Association for Computational Linguistics.
Cite (Informal):
DiDi Labs’ End-to-end System for the IWSLT 2020 Offline Speech TranslationTask (Arkhangorodsky et al., IWSLT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwslt-1.6.pdf
Video:
 http://slideslive.com/38929593