Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

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

Abstract

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
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-01408086 , version 1

Cite

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⟩
646 View
685 Download

Share

Gmail Facebook X LinkedIn More