Detail publikace

The IWSLT 2021 BUT Speech Translation Systems

VYDANA, H. KARAFIÁT, M. BURGET, L. ČERNOCKÝ, J.

Originální název

The IWSLT 2021 BUT Speech Translation Systems

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

The paper describes BUTs English to German offline speech translation (ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition- Machine Translation models. Their performances is evaluated on MustC-Common test set. In this work, we study their efficiency from the perspective of having a large amount of separate ASR training data and MT training data, and a smaller amount of speechtranslation training data. Large amounts of ASR and MT training data are utilized for pretraining the ASR and MT models. Speechtranslation data is used to jointly optimize ASR-MT models by defining an end-to-end differentiable path from speech to translations. For this purpose, we use the internal continuous representations from the ASR-decoder as the input to MT module. We show that speech translation can be further improved by training the ASR-decoder jointly with the MT-module using large amount of text-only MT training data. We also show significant improvements by training an ASR module capable of generating punctuated text, rather than leaving the punctuation task to the MT module.

Klíčová slova

speech, translation

Autoři

VYDANA, H.; KARAFIÁT, M.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

5. 8. 2021

Nakladatel

Association for Computational Linguistics

Místo

Bangkok, on-line

ISBN

978-1-7138-3378-9

Kniha

Proceedings of 18th International Conference on Spoken Language Translation (IWSLT)

Strany od

75

Strany do

83

Strany počet

9

URL

https://aclanthology.org/2021.iwslt-1.7.pdf

BibTex

@inproceedings{BUT177246,
  author="Hari Krishna {Vydana} and Martin {Karafiát} and Lukáš {Burget} and Jan {Černocký}",
  title="The IWSLT 2021 BUT Speech Translation Systems",
  booktitle="Proceedings of 18th International Conference on Spoken Language Translation (IWSLT)",
  year="2021",
  pages="75--83",
  publisher="Association for Computational Linguistics",
  address="Bangkok, on-line",
  doi="10.18653/v1/2021.iwslt-1.7",
  isbn="978-1-7138-3378-9",
  url="https://aclanthology.org/2021.iwslt-1.7.pdf"
}