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
- 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)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.iwslt-1.13.pdf
- Data
- How2, LibriSpeech, MuST-C, TED-LIUM 3