Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation

Résumé

This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language text during learning or decoding. Relaxing the need for source language transcription would drastically change the data collection methodology in speech translation, especially in under-resourced scenarios.
Fichier principal
Vignette du fichier
listen_and_translate_nips_2016_final.pdf (297.95 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01408086 , version 1 (06-12-2016)

Identifiants

  • HAL Id : hal-01408086 , version 1

Citer

Alexandre Bérard, Olivier Pietquin, Laurent Besacier, Christophe Servan. Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation. NIPS Workshop on end-to-end learning for speech and audio processing, Dec 2016, Barcelona, Spain. ⟨hal-01408086⟩
649 Consultations
702 Téléchargements

Partager

Gmail Facebook X LinkedIn More