Efficient yet Competitive Speech Translation: FBK@IWSLT2022

Marco Gaido, Sara Papi, Dennis Fucci, Giuseppe Fiameni, Matteo Negri, Marco Turchi

Abstract
The primary goal of this FBK’s systems submission to the IWSLT 2022 offline and simultaneous speech translation tasks is to reduce model training costs without sacrificing translation quality. As such, we first question the need of ASR pre-training, showing that it is not essential to achieve competitive results. Second, we focus on data filtering, showing that a simple method that looks at the ratio between source and target characters yields a quality improvement of 1 BLEU. Third, we compare different methods to reduce the detrimental effect of the audio segmentation mismatch between training data manually segmented at sentence level and inference data that is automatically segmented. Towards the same goal of training cost reduction, we participate in the simultaneous task with the same model trained for offline ST. The effectiveness of our lightweight training strategy is shown by the high score obtained on the MuST-C en-de corpus (26.7 BLEU) and is confirmed in high-resource data conditions by a 1.6 BLEU improvement on the IWSLT2020 test set over last year’s winning system.
Anthology ID:
2022.iwslt-1.13
Volume:
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
Month:
May
Year:
2022
Address:
Dublin, Ireland (in-person and online)
Venue:
IWSLT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
177–189
Language:
URL:
https://aclanthology.org/2022.iwslt-1.13
DOI:
10.18653/v1/2022.iwslt-1.13
Bibkey:
Cite (ACL):
Marco Gaido, Sara Papi, Dennis Fucci, Giuseppe Fiameni, Matteo Negri, and Marco Turchi. 2022. Efficient yet Competitive Speech Translation: FBK@IWSLT2022. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 177–189, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
Cite (Informal):
Efficient yet Competitive Speech Translation: FBK@IWSLT2022 (Gaido et al., IWSLT 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2022.iwslt-1.13.pdf
Code
 hlt-mt/fbk-fairseq
PDF Search Code