KIT’s Multilingual Speech Translation System for IWSLT 2023

Danni Liu, Thai Binh Nguyen, Sai Koneru, Enes Yavuz Ugan, Ngoc-Quan Pham, Tuan Nam Nguyen, Tu Anh Dinh, Carlos Mullov, Alexander Waibel, Jan Niehues

Abstract
Many existing speech translation benchmarks focus on native-English speech in high-quality recording conditions, which often do not match the conditions in real-life use-cases. In this paper, we describe our speech translation system for the multilingual track of IWSLT 2023, which focuses on the translation of scientific conference talks. The test condition features accented input speech and terminology-dense contents. The tasks requires translation into 10 languages of varying amounts of resources. In absence of training data from the target domain, we use a retrieval-based approach (kNN-MT) for effective adaptation (+0.8 BLEU for speech translation). We also use adapters to easily integrate incremental training data from data augmentation, and show that it matches the performance of re-training. We observe that cascaded systems are more easily adaptable towards specific target domains, due to their separate modules. Our cascaded speech system outperforms its end-to-end counterpart on scientific talk translation, although their performance remains similar on TED talks.
Anthology ID:
2023.iwslt-1.6
Volume:
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada (in-person and online)
Venue:
IWSLT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
113–122
Language:
URL:
https://aclanthology.org/2023.iwslt-1.6
DOI:
Bibkey:
Cite (ACL):
Danni Liu, Thai Binh Nguyen, Sai Koneru, Enes Yavuz Ugan, Ngoc-Quan Pham, Tuan Nam Nguyen, Tu Anh Dinh, Carlos Mullov, Alexander Waibel, and Jan Niehues. 2023. KIT’s Multilingual Speech Translation System for IWSLT 2023. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 113–122, Toronto, Canada (in-person and online). Association for Computational Linguistics.
Cite (Informal):
KIT’s Multilingual Speech Translation System for IWSLT 2023 (Liu et al., IWSLT 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2023.iwslt-1.6.pdf
PDF Search