Abstract
This paper describes Maastricht University’s participation in the IWSLT 2021 multilingual speech translation track. The task in this track is to build multilingual speech translation systems in supervised and zero-shot directions. Our primary system is an end-to-end model that performs both speech transcription and translation. We observe that the joint training for the two tasks is complementary especially when the speech translation data is scarce. On the source and target side, we use data augmentation and pseudo-labels respectively to improve the performance of our systems. We also introduce an ensembling technique that consistently improves the quality of transcriptions and translations. The experiments show that the end-to-end system is competitive with its cascaded counterpart especially in zero-shot conditions.- Anthology ID:
- 2021.iwslt-1.15
- 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:
- 138–143
- Language:
- URL:
- https://aclanthology.org/2021.iwslt-1.15
- DOI:
- 10.18653/v1/2021.iwslt-1.15
- Cite (ACL):
- Danni Liu and Jan Niehues. 2021. Maastricht University’s Multilingual Speech Translation System for IWSLT 2021. In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), pages 138–143, Bangkok, Thailand (online). Association for Computational Linguistics.
- Cite (Informal):
- Maastricht University’s Multilingual Speech Translation System for IWSLT 2021 (Liu & Niehues, IWSLT 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.iwslt-1.15.pdf