Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Khurana, Sameer, Dawalatabad, Nauman, Laurent, Antoine, Vicente, Luis, Gimeno, Pablo, Mingote, Victoria, Glass, James
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2306.00789
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917573596020736
author Khurana, Sameer
Dawalatabad, Nauman
Laurent, Antoine
Vicente, Luis
Gimeno, Pablo
Mingote, Victoria
Glass, James
author_facet Khurana, Sameer
Dawalatabad, Nauman
Laurent, Antoine
Vicente, Luis
Gimeno, Pablo
Mingote, Victoria
Glass, James
contents Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text translation via semantic knowledge distillation. We show that by initializing the encoder of the encoder-decoder sequence-to-sequence translation model with SAMU-XLS-R, a multilingual speech transformer encoder trained using multi-modal (speech-text) semantic knowledge distillation, we achieve significantly better cross-lingual task knowledge transfer than the baseline XLS-R, a multilingual speech transformer encoder trained via self-supervised learning. We demonstrate the effectiveness of our approach on two popular datasets, namely, CoVoST-2 and Europarl. On the 21 translation tasks of the CoVoST-2 benchmark, we achieve an average improvement of 12.8 BLEU points over the baselines. In the zero-shot translation scenario, we achieve an average gain of 18.8 and 11.9 average BLEU points on unseen medium and low-resource languages. We make similar observations on Europarl speech translation benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2306_00789
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improved Cross-Lingual Transfer Learning For Automatic Speech Translation
Khurana, Sameer
Dawalatabad, Nauman
Laurent, Antoine
Vicente, Luis
Gimeno, Pablo
Mingote, Victoria
Glass, James
Computation and Language
Artificial Intelligence
Audio and Speech Processing
Signal Processing
Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text translation via semantic knowledge distillation. We show that by initializing the encoder of the encoder-decoder sequence-to-sequence translation model with SAMU-XLS-R, a multilingual speech transformer encoder trained using multi-modal (speech-text) semantic knowledge distillation, we achieve significantly better cross-lingual task knowledge transfer than the baseline XLS-R, a multilingual speech transformer encoder trained via self-supervised learning. We demonstrate the effectiveness of our approach on two popular datasets, namely, CoVoST-2 and Europarl. On the 21 translation tasks of the CoVoST-2 benchmark, we achieve an average improvement of 12.8 BLEU points over the baselines. In the zero-shot translation scenario, we achieve an average gain of 18.8 and 11.9 average BLEU points on unseen medium and low-resource languages. We make similar observations on Europarl speech translation benchmark.
title Improved Cross-Lingual Transfer Learning For Automatic Speech Translation
topic Computation and Language
Artificial Intelligence
Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2306.00789