@inproceedings{papi-etal-2024-simulseamless,
title = "{S}imul{S}eamless: {FBK} at {IWSLT} 2024 Simultaneous Speech Translation",
author = "Papi, Sara and
Gaido, Marco and
Negri, Matteo and
Bentivogli, Luisa",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwslt-1.11",
doi = "10.18653/v1/2024.iwslt-1.11",
pages = "72--79",
abstract = "This paper describes the FBK{'}s participation in the Simultaneous Translation Evaluation Campaign at IWSLT 2024. For this year{'}s submission in the speech-to-text translation (ST) sub-track, we propose SimulSeamless, which is realized by combining AlignAtt and SeamlessM4T in its medium configuration. The SeamlessM4T model is used {`}off-the-shelf{'} and its simultaneous inference is enabled through the adoption of AlignAtt, a SimulST policy based on cross-attention that can be applied without any retraining or adaptation of the underlying model for the simultaneous task. We participated in all the Shared Task languages (English-{\textgreater}German, Japanese, Chinese, and Czech-{\textgreater}English), achieving acceptable or even better results compared to last year{'}s submissions. SimulSeamless, covering more than 143 source languages and 200 target languages, is released at: https://github.com/hlt-mt/FBK-fairseq/.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papi-etal-2024-simulseamless">
<titleInfo>
<title>SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Papi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)</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">Bangkok, Thailand (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the FBK’s participation in the Simultaneous Translation Evaluation Campaign at IWSLT 2024. For this year’s submission in the speech-to-text translation (ST) sub-track, we propose SimulSeamless, which is realized by combining AlignAtt and SeamlessM4T in its medium configuration. The SeamlessM4T model is used ‘off-the-shelf’ and its simultaneous inference is enabled through the adoption of AlignAtt, a SimulST policy based on cross-attention that can be applied without any retraining or adaptation of the underlying model for the simultaneous task. We participated in all the Shared Task languages (English-\textgreaterGerman, Japanese, Chinese, and Czech-\textgreaterEnglish), achieving acceptable or even better results compared to last year’s submissions. SimulSeamless, covering more than 143 source languages and 200 target languages, is released at: https://github.com/hlt-mt/FBK-fairseq/.</abstract>
<identifier type="citekey">papi-etal-2024-simulseamless</identifier>
<identifier type="doi">10.18653/v1/2024.iwslt-1.11</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.11</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>72</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
%A Papi, Sara
%A Gaido, Marco
%A Negri, Matteo
%A Bentivogli, Luisa
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (in-person and online)
%F papi-etal-2024-simulseamless
%X This paper describes the FBK’s participation in the Simultaneous Translation Evaluation Campaign at IWSLT 2024. For this year’s submission in the speech-to-text translation (ST) sub-track, we propose SimulSeamless, which is realized by combining AlignAtt and SeamlessM4T in its medium configuration. The SeamlessM4T model is used ‘off-the-shelf’ and its simultaneous inference is enabled through the adoption of AlignAtt, a SimulST policy based on cross-attention that can be applied without any retraining or adaptation of the underlying model for the simultaneous task. We participated in all the Shared Task languages (English-\textgreaterGerman, Japanese, Chinese, and Czech-\textgreaterEnglish), achieving acceptable or even better results compared to last year’s submissions. SimulSeamless, covering more than 143 source languages and 200 target languages, is released at: https://github.com/hlt-mt/FBK-fairseq/.
%R 10.18653/v1/2024.iwslt-1.11
%U https://aclanthology.org/2024.iwslt-1.11
%U https://doi.org/10.18653/v1/2024.iwslt-1.11
%P 72-79
Markdown (Informal)
[SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation](https://aclanthology.org/2024.iwslt-1.11) (Papi et al., IWSLT 2024)
ACL
- Sara Papi, Marco Gaido, Matteo Negri, and Luisa Bentivogli. 2024. SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 72–79, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.