@inproceedings{mohammadamini-tahon-2026-lium,
title = "{LIUM} Submission for {IWSLT} 2026 Low-resource Speech Translation Track",
author = "Mohammadamini, Mohammad and
Tahon, Marie",
editor = "Salesky, Elizabeth and
Anastasopoulos, Antonios and
Negri, Matteo and
Federico, Marcello",
booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
month = jul,
year = "2026",
address = "San Diego, USA (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwslt-1.15/",
pages = "124--131",
ISBN = "979-8-89176-411-8",
abstract = "This paper describes the LIUM submission to the IWSLT 2026 low-resource speech translation track. It proposes different data augmentation methods for low-resource speech-to-text translation, including two main pipelines: pseudo-labeling and speech synthesis. The goal is to generate parallel speech data in low-resource scenarios without relying on human-annotated speech translation data. Our submission focuses on Central Kurdish{--}English language pairs. The objective of this work is to explore the advantages and limitations of each data augmentation method. Our best results are obtained using the pseudo-labeling pipeline, achieving a BLEU score of 25.73 on the development set and 21.09 on the test set for Central Kurdish{--}English translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohammadamini-tahon-2026-lium">
<titleInfo>
<title>LIUM Submission for IWSLT 2026 Low-resource Speech Translation Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Mohammadamini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Tahon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)</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">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-411-8</identifier>
</relatedItem>
<abstract>This paper describes the LIUM submission to the IWSLT 2026 low-resource speech translation track. It proposes different data augmentation methods for low-resource speech-to-text translation, including two main pipelines: pseudo-labeling and speech synthesis. The goal is to generate parallel speech data in low-resource scenarios without relying on human-annotated speech translation data. Our submission focuses on Central Kurdish–English language pairs. The objective of this work is to explore the advantages and limitations of each data augmentation method. Our best results are obtained using the pseudo-labeling pipeline, achieving a BLEU score of 25.73 on the development set and 21.09 on the test set for Central Kurdish–English translation.</abstract>
<identifier type="citekey">mohammadamini-tahon-2026-lium</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.15/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>124</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LIUM Submission for IWSLT 2026 Low-resource Speech Translation Track
%A Mohammadamini, Mohammad
%A Tahon, Marie
%Y Salesky, Elizabeth
%Y Anastasopoulos, Antonios
%Y Negri, Matteo
%Y Federico, Marcello
%S Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA (in-person and online)
%@ 979-8-89176-411-8
%F mohammadamini-tahon-2026-lium
%X This paper describes the LIUM submission to the IWSLT 2026 low-resource speech translation track. It proposes different data augmentation methods for low-resource speech-to-text translation, including two main pipelines: pseudo-labeling and speech synthesis. The goal is to generate parallel speech data in low-resource scenarios without relying on human-annotated speech translation data. Our submission focuses on Central Kurdish–English language pairs. The objective of this work is to explore the advantages and limitations of each data augmentation method. Our best results are obtained using the pseudo-labeling pipeline, achieving a BLEU score of 25.73 on the development set and 21.09 on the test set for Central Kurdish–English translation.
%U https://aclanthology.org/2026.iwslt-1.15/
%P 124-131
Markdown (Informal)
[LIUM Submission for IWSLT 2026 Low-resource Speech Translation Track](https://aclanthology.org/2026.iwslt-1.15/) (Mohammadamini & Tahon, IWSLT 2026)
ACL