ON-TRAC' systems for the IWSLT 2021 low-resource speech translation and multilingual speech translation shared tasks - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

ON-TRAC' systems for the IWSLT 2021 low-resource speech translation and multilingual speech translation shared tasks

Abstract

This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2021, low-resource speech translation and multilingual speech translation. The ON-TRAC Consortium is composed of researchers from three French academic laboratories and an industrial partner: LIA (Avignon Université), LIG (Université Grenoble Alpes), LIUM (Le Mans Université), and researchers from Airbus. A pipeline approach was explored for the lowresource speech translation task, using a hybrid HMM/TDNN automatic speech recognition system fed by wav2vec features, coupled to an NMT system. For the multilingual speech translation task, we investigated the use of a dual-decoder Transformer that jointly transcribes and translates an input speech signal. This model was trained in order to translate from multiple source languages to multiple target ones.
Fichier principal
Vignette du fichier
v2--ON_TRAC_IWSLT21.pdf (139.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03298854 , version 1 (24-07-2021)
hal-03298854 , version 2 (29-07-2021)

Identifiers

Cite

Hang Le, Florentin Barbier, Ha Nguyen, Natalia Tomashenko, Salima Mdhaffar, et al.. ON-TRAC' systems for the IWSLT 2021 low-resource speech translation and multilingual speech translation shared tasks. International Conference on Spoken Language Translation (IWSLT), Aug 2021, Bangkok (virtual), Thailand. ⟨10.18653/v1/2021.iwslt-1.20⟩. ⟨hal-03298854v2⟩
275 View
213 Download

Altmetric

Share

Gmail Facebook X LinkedIn More