End-to-End Automatic Speech Translation of Audiobooks

Bérard, Alexandre; Besacier, Laurent; Kocabiyikoglu, Ali Can; Pietquin, Olivier

Document type :

Communication dans un congrès avec actes

Title :

End-to-End Automatic Speech Translation of Audiobooks

Author(s) :

Bérard, Alexandre [Auteur]
Laboratoire d'Informatique de Grenoble [LIG ]
Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole [GETALP ]
Institut universitaire de France [IUF]
Besacier, Laurent [Auteur]
Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole [GETALP ]
Institut universitaire de France [IUF]
Laboratoire d'Informatique de Grenoble [LIG ]
Kocabiyikoglu, Ali Can [Auteur]
Laboratoire d'Informatique de Grenoble [LIG ]
Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole [GETALP ]
Pietquin, Olivier [Auteur]
DeepMind Technologies
Sequential Learning [SEQUEL]

Conference title :

ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing

City :

Calgary, Alberta

Country :

Canada

Start date of the conference :

2018-04-15

English keyword(s) :

End-to-end models
Speech Translation
LibriSpeech

HAL domain(s) :

Informatique [cs]/Informatique et langage [cs.CL]

English abstract : [en]

We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task. Previous works investigated the extreme case where source language transcription is not available during ...
Show more >We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task. Previous works investigated the extreme case where source language transcription is not available during learning nor decoding , but we also study a midway case where source language transcription is available at training time only. In this case, a single model is trained to decode source speech into target text in a single pass. Experimental results show that it is possible to train compact and efficient end-to-end speech translation models in this setup. We also distribute the corpus and hope that our speech translation baseline on this corpus will be challenged in the future.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Méthodes qualité avancées pour la post-édition de traduction automatique
Systemes et Algorithmes Pervasifs au confluent des mondes physique et numérique

Collections :