KIT’s IWSLT 2021 Offline Speech Translation System

Tuan Nam Nguyen, Thai Son Nguyen, Christian Huber, Ngoc-Quan Pham, Thanh-Le Ha, Felix Schneider, Sebastian Stüker


Abstract
This paper describes KIT’submission to the IWSLT 2021 Offline Speech Translation Task. We describe a system in both cascaded condition and end-to-end condition. In the cascaded condition, we investigated different end-to-end architectures for the speech recognition module. For the text segmentation module, we trained a small transformer-based model on high-quality monolingual data. For the translation module, our last year’s neural machine translation model was reused. In the end-to-end condition, we improved our Speech Relative Transformer architecture to reach or even surpass the result of the cascade system.
Anthology ID:
2021.iwslt-1.13
Volume:
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
Month:
August
Year:
2021
Address:
Bangkok, Thailand (online)
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
125–130
Language:
URL:
https://aclanthology.org/2021.iwslt-1.13
DOI:
10.18653/v1/2021.iwslt-1.13
Bibkey:
Cite (ACL):
Tuan Nam Nguyen, Thai Son Nguyen, Christian Huber, Ngoc-Quan Pham, Thanh-Le Ha, Felix Schneider, and Sebastian Stüker. 2021. KIT’s IWSLT 2021 Offline Speech Translation System. In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), pages 125–130, Bangkok, Thailand (online). Association for Computational Linguistics.
Cite (Informal):
KIT’s IWSLT 2021 Offline Speech Translation System (Nguyen et al., IWSLT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.iwslt-1.13.pdf
Data
How2LibriSpeechMuST-CTED-LIUM 3