Abstract
We present a new task, speech dialogue translation mediating speakers of different languages. We construct the SpeechBSD dataset for the task and conduct baseline experiments. Furthermore, we consider context to be an important aspect that needs to be addressed in this task and propose two ways of utilizing context, namely monolingual context and bilingual context. We conduct cascaded speech translation experiments using Whisper and mBART, and show that bilingual context performs better in our settings.- Anthology ID:
- 2023.findings-acl.72
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1122–1134
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.72
- DOI:
- 10.18653/v1/2023.findings-acl.72
- Cite (ACL):
- Shuichiro Shimizu, Chenhui Chu, Sheng Li, and Sadao Kurohashi. 2023. Towards Speech Dialogue Translation Mediating Speakers of Different Languages. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1122–1134, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Towards Speech Dialogue Translation Mediating Speakers of Different Languages (Shimizu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2023.findings-acl.72.pdf