Tutorial: End-to-End Speech Translation

Jan Niehues, Elizabeth Salesky, Marco Turchi, Matteo Negri


Abstract
Speech translation is the translation of speech in one language typically to text in another, traditionally accomplished through a combination of automatic speech recognition and machine translation. Speech translation has attracted interest for many years, but the recent successful applications of deep learning to both individual tasks have enabled new opportunities through joint modeling, in what we today call ‘end-to-end speech translation.’ In this tutorial we introduce the techniques used in cutting-edge research on speech translation. Starting from the traditional cascaded approach, we give an overview on data sources and model architectures to achieve state-of-the art performance with end-to-end speech translation for both high- and low-resource languages. In addition, we discuss methods to evaluate analyze the proposed solutions, as well as the challenges faced when applying speech translation models for real-world applications.
Anthology ID:
2021.eacl-tutorials.3
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts
Month:
April
Year:
2021
Address:
online
Editors:
Isabelle Augenstein, Ivan Habernal
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10–13
Language:
URL:
https://aclanthology.org/2021.eacl-tutorials.3
DOI:
10.18653/v1/2021.eacl-tutorials.3
Bibkey:
Cite (ACL):
Jan Niehues, Elizabeth Salesky, Marco Turchi, and Matteo Negri. 2021. Tutorial: End-to-End Speech Translation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts, pages 10–13, online. Association for Computational Linguistics.
Cite (Informal):
Tutorial: End-to-End Speech Translation (Niehues et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-tutorials.3.pdf