تقرير
Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23
| العنوان: | Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23 |
|---|---|
| المؤلفون: | Tsiamas, Ioannis, Gállego, Gerard I., Fonollosa, José A. R., Costa-jussà, Marta R. |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
| الوصف: | This paper describes the submission of the UPC Machine Translation group to the IWSLT 2023 Offline Speech Translation task. Our Speech Translation systems utilize foundation models for speech (wav2vec 2.0) and text (mBART50). We incorporate a Siamese pretraining step of the speech and text encoders with CTC and Optimal Transport, to adapt the speech representations to the space of the text model, thus maximizing transfer learning from MT. After this pretraining, we fine-tune our system end-to-end on ST, with Cross Entropy and Knowledge Distillation. Apart from the available ST corpora, we create synthetic data with SegAugment to better adapt our models to the custom segmentations of the IWSLT test sets. Our best single model obtains 31.2 BLEU points on MuST-C tst-COMMON, 29.8 points on IWLST.tst2020 and 33.4 points on the newly released IWSLT.ACLdev2023. Comment: IWSLT 2023 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2306.01327 |
| رقم الأكسشن: | edsarx.2306.01327 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |