Abstract
In this paper, we present our submission to the Non-Native Speech Translation Task for IWSLT 2020. Our main contribution is a proposed speech recognition pipeline that consists of an acoustic model and a phoneme-to-grapheme model. As an intermediate representation, we utilize phonemes. We demonstrate that the proposed pipeline surpasses commercially used automatic speech recognition (ASR) and submit it into the ASR track. We complement this ASR with off-the-shelf MT systems to take part also in the speech translation track.- Anthology ID:
- 2020.iwslt-1.24
- Volume:
- Proceedings of the 17th International Conference on Spoken Language Translation
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Marcello Federico, Alex Waibel, Kevin Knight, Satoshi Nakamura, Hermann Ney, Jan Niehues, Sebastian Stüker, Dekai Wu, Joseph Mariani, Francois Yvon
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 191–199
- Language:
- URL:
- https://aclanthology.org/2020.iwslt-1.24
- DOI:
- 10.18653/v1/2020.iwslt-1.24
- Cite (ACL):
- Peter Polák, Sangeet Sagar, Dominik Macháček, and Ondřej Bojar. 2020. CUNI Neural ASR with Phoneme-Level Intermediate Step for~Non-Native~SLT at IWSLT 2020. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 191–199, Online. Association for Computational Linguistics.
- Cite (Informal):
- CUNI Neural ASR with Phoneme-Level Intermediate Step for~Non-Native~SLT at IWSLT 2020 (Polák et al., IWSLT 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.iwslt-1.24.pdf