The KIT Speech Translation Systems for IWSLT 2024 Dialectal and Low-resource Track

Zhaolin Li, Enes Yavuz Ugan, Danni Liu, Carlos Mullov, Tu Anh Dinh, Sai Koneru, Alexander Waibel, Jan Niehues

Abstract
This paper presents KIT’s submissions to the IWSLT 2024 dialectal and low-resource track. In this work, we build systems for translating into English from speech in Maltese, Bemba, and two Arabic dialects Tunisian and North Levantine. Under the unconstrained condition, we leverage the pre-trained multilingual models by fine-tuning them for the target language pairs to address data scarcity problems in this track. We build cascaded and end-to-end speech translation systems for different language pairs and show the cascaded system brings slightly better overall performance. Besides, we find utilizing additional data resources boosts speech recognition performance but slightly harms machine translation performance in cascaded systems. Lastly, we show that Minimum Bayes Risk is effective in improving speech translation performance by combining the cascaded and end-to-end systems, bringing a consistent improvement of around 1 BLUE point.
Anthology ID:
2024.iwslt-1.27
Volume:
Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand (in-person and online)
Editors:
Elizabeth Salesky, Marcello Federico, Marine Carpuat
Venue:
IWSLT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
221–228
Language:
URL:
https://aclanthology.org/2024.iwslt-1.27
DOI:
10.18653/v1/2024.iwslt-1.27
Bibkey:
Cite (ACL):
Zhaolin Li, Enes Yavuz Ugan, Danni Liu, Carlos Mullov, Tu Anh Dinh, Sai Koneru, Alexander Waibel, and Jan Niehues. 2024. The KIT Speech Translation Systems for IWSLT 2024 Dialectal and Low-resource Track. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 221–228, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.
Cite (Informal):
The KIT Speech Translation Systems for IWSLT 2024 Dialectal and Low-resource Track (Li et al., IWSLT 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/2024.iwslt-1.27.pdf
PDF Search Fix metadata