The USTC-NEL Speech Translation system at IWSLT 2018
Dan Liu, Junhua Liu, Wu Guo, Shifu Xiong, Zhiqiang Ma, Rui Song, Chongliang Wu, Quan Liu
Abstract
This paper describes the USTC-NEL (short for ”National Engineering Laboratory for Speech and Language Information Processing University of science and technology of china”) system to the speech translation task of the IWSLT Evaluation 2018. The system is a conventional pipeline system which contains 3 modules: speech recognition, post-processing and machine translation. We train a group of hybrid-HMM models for our speech recognition, and for machine translation we train transformer based neural machine translation models with speech recognition output style text as input. Experiments conducted on the IWSLT 2018 task indicate that, compared to baseline system from KIT, our system achieved 14.9 BLEU improvement.- Anthology ID:
- 2018.iwslt-1.10
- Volume:
- Proceedings of the 15th International Conference on Spoken Language Translation
- Month:
- October 29-30
- Year:
- 2018
- Address:
- Brussels
- Editors:
- Marco Turchi, Jan Niehues, Marcello Frederico
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- International Conference on Spoken Language Translation
- Note:
- Pages:
- 70–75
- Language:
- URL:
- https://aclanthology.org/2018.iwslt-1.10
- DOI:
- Cite (ACL):
- Dan Liu, Junhua Liu, Wu Guo, Shifu Xiong, Zhiqiang Ma, Rui Song, Chongliang Wu, and Quan Liu. 2018. The USTC-NEL Speech Translation system at IWSLT 2018. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 70–75, Brussels. International Conference on Spoken Language Translation.
- Cite (Informal):
- The USTC-NEL Speech Translation system at IWSLT 2018 (Liu et al., IWSLT 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2018.iwslt-1.10.pdf