@inproceedings{laurent-etal-2023-trac,
title = "{ON}-{TRAC} Consortium Systems for the {IWSLT} 2023 Dialectal and Low-resource Speech Translation Tasks",
author = {Laurent, Antoine and
Gahbiche, Souhir and
Nguyen, Ha and
Elleuch, Haroun and
Bougares, Fethi and
Thiol, Antoine and
Riguidel, Hugo and
Mdhaffar, Salima and
Laperri{\`e}re, Ga{\"e}lle and
Maison, Lucas and
Khurana, Sameer and
Est{\`e}ve, Yannick},
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwslt-1.18",
doi = "10.18653/v1/2023.iwslt-1.18",
pages = "219--226",
abstract = "This paper describes the ON-TRAC consortium speech translation systems developed for IWSLT 2023 evaluation campaign. Overall, we participated in three speech translation tracks featured in the low-resource and dialect speech translation shared tasks, namely; i) spoken Tamasheq to written French, ii) spoken Pashto to written French, and iii) spoken Tunisian to written English. All our primary submissions are based on the end-to-end speech-to-text neural architecture using a pretrained SAMU-XLSR model as a speech encoder and a mbart model as a decoder. The SAMU-XLSR model is built from the XLS-R 128 in order to generate language agnostic sentence-level embeddings. This building is driven by the LaBSE model trained on multilingual text dataset. This architecture allows us to improve the input speech representations and achieve significant improvements compared to conventional end-to-end speech translation systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laurent-etal-2023-trac">
<titleInfo>
<title>ON-TRAC Consortium Systems for the IWSLT 2023 Dialectal and Low-resource Speech Translation Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Laurent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Souhir</namePart>
<namePart type="family">Gahbiche</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ha</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haroun</namePart>
<namePart type="family">Elleuch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Thiol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Riguidel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salima</namePart>
<namePart type="family">Mdhaffar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaëlle</namePart>
<namePart type="family">Laperrière</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Maison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Khurana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannick</namePart>
<namePart type="family">Estève</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the ON-TRAC consortium speech translation systems developed for IWSLT 2023 evaluation campaign. Overall, we participated in three speech translation tracks featured in the low-resource and dialect speech translation shared tasks, namely; i) spoken Tamasheq to written French, ii) spoken Pashto to written French, and iii) spoken Tunisian to written English. All our primary submissions are based on the end-to-end speech-to-text neural architecture using a pretrained SAMU-XLSR model as a speech encoder and a mbart model as a decoder. The SAMU-XLSR model is built from the XLS-R 128 in order to generate language agnostic sentence-level embeddings. This building is driven by the LaBSE model trained on multilingual text dataset. This architecture allows us to improve the input speech representations and achieve significant improvements compared to conventional end-to-end speech translation systems.</abstract>
<identifier type="citekey">laurent-etal-2023-trac</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.18</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.18</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>219</start>
<end>226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ON-TRAC Consortium Systems for the IWSLT 2023 Dialectal and Low-resource Speech Translation Tasks
%A Laurent, Antoine
%A Gahbiche, Souhir
%A Nguyen, Ha
%A Elleuch, Haroun
%A Bougares, Fethi
%A Thiol, Antoine
%A Riguidel, Hugo
%A Mdhaffar, Salima
%A Laperrière, Gaëlle
%A Maison, Lucas
%A Khurana, Sameer
%A Estève, Yannick
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F laurent-etal-2023-trac
%X This paper describes the ON-TRAC consortium speech translation systems developed for IWSLT 2023 evaluation campaign. Overall, we participated in three speech translation tracks featured in the low-resource and dialect speech translation shared tasks, namely; i) spoken Tamasheq to written French, ii) spoken Pashto to written French, and iii) spoken Tunisian to written English. All our primary submissions are based on the end-to-end speech-to-text neural architecture using a pretrained SAMU-XLSR model as a speech encoder and a mbart model as a decoder. The SAMU-XLSR model is built from the XLS-R 128 in order to generate language agnostic sentence-level embeddings. This building is driven by the LaBSE model trained on multilingual text dataset. This architecture allows us to improve the input speech representations and achieve significant improvements compared to conventional end-to-end speech translation systems.
%R 10.18653/v1/2023.iwslt-1.18
%U https://aclanthology.org/2023.iwslt-1.18
%U https://doi.org/10.18653/v1/2023.iwslt-1.18
%P 219-226
Markdown (Informal)
[ON-TRAC Consortium Systems for the IWSLT 2023 Dialectal and Low-resource Speech Translation Tasks](https://aclanthology.org/2023.iwslt-1.18) (Laurent et al., IWSLT 2023)
ACL
- Antoine Laurent, Souhir Gahbiche, Ha Nguyen, Haroun Elleuch, Fethi Bougares, Antoine Thiol, Hugo Riguidel, Salima Mdhaffar, Gaëlle Laperrière, Lucas Maison, Sameer Khurana, and Yannick Estève. 2023. ON-TRAC Consortium Systems for the IWSLT 2023 Dialectal and Low-resource Speech Translation Tasks. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 219–226, Toronto, Canada (in-person and online). Association for Computational Linguistics.