The Kyoto Speech-to-Speech Translation System for IWSLT 2023
Zhengdong Yang, Shuichiro Shimizu, Wangjin Zhou, Sheng Li, Chenhui Chu
Abstract
This paper describes the Kyoto speech-to-speech translation system for IWSLT 2023. Our system is a combination of speech-to-text translation and text-to-speech synthesis. For the speech-to-text translation model, we used the dual-decoderTransformer model. For text-to-speech synthesis model, we took a cascade approach of an acoustic model and a vocoder.- Anthology ID:
- 2023.iwslt-1.33
- Volume:
- Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada (in-person and online)
- Editors:
- Elizabeth Salesky, Marcello Federico, Marine Carpuat
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 357–362
- Language:
- URL:
- https://aclanthology.org/2023.iwslt-1.33
- DOI:
- 10.18653/v1/2023.iwslt-1.33
- Cite (ACL):
- Zhengdong Yang, Shuichiro Shimizu, Wangjin Zhou, Sheng Li, and Chenhui Chu. 2023. The Kyoto Speech-to-Speech Translation System for IWSLT 2023. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 357–362, Toronto, Canada (in-person and online). Association for Computational Linguistics.
- Cite (Informal):
- The Kyoto Speech-to-Speech Translation System for IWSLT 2023 (Yang et al., IWSLT 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.iwslt-1.33.pdf