Enes Yavuz Ugan
2023
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
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
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.
Search
Co-authors
- Danni Liu 1
- Thai-Binh Nguyen 1
- Sai Koneru 1
- Ngoc-Quan Pham 1
- Tuan-Nam Nguyen 1
- show all...