@inproceedings{e-ortega-etal-2025-quespa,
title = "{QUESPA} Submission for the {IWSLT} 2025 Dialectal and Low-resource Speech Translation Task",
author = "Ortega, John E. and
Joel Zevallos, Rodolfo and
Chen, William and
Abdulmumin, Idris",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Anastasopoulos, Antonis",
booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.iwslt-1.25/",
doi = "10.18653/v1/2025.iwslt-1.25",
pages = "260--268",
ISBN = "979-8-89176-272-5",
abstract = "This article describes the QUESPA team speech translation (ST) submissions for the Quechua to Spanish (QUE-SPA) track featured in the Evaluation Campaign of IWSLT 2025: dialectal and low-resource speech translation. This year, there is one main submission type supported in the campaign: unconstrained. This is our third year submitting our ST systems to the IWSLT shared task and we feel that we have achieved novel performance, surpassing last year{'}s submission. This year we submit three total unconstrained-only systems of which our best (contrastive 2) system uses last year{'}s best performing pre-trained language (PLM) model for ST (without cascading) and the inclusion of additional Quechua{--}Collao speech transcriptions found online. Fine-tuning of Microsoft{'}s SpeechT5 model in a ST setting along with the addition of new data and a data augmentation technique allowed us to achieve 26.7 BLEU. In this article, we present the three submissions along with a detailed description of the updated machine translation system where a comparison is done between synthetic, unconstrained, and other data for fine-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="e-ortega-etal-2025-quespa">
<titleInfo>
<title>QUESPA Submission for the IWSLT 2025 Dialectal and Low-resource Speech Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodolfo</namePart>
<namePart type="family">Joel Zevallos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Abdulmumin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)</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">Antonis</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-272-5</identifier>
</relatedItem>
<abstract>This article describes the QUESPA team speech translation (ST) submissions for the Quechua to Spanish (QUE-SPA) track featured in the Evaluation Campaign of IWSLT 2025: dialectal and low-resource speech translation. This year, there is one main submission type supported in the campaign: unconstrained. This is our third year submitting our ST systems to the IWSLT shared task and we feel that we have achieved novel performance, surpassing last year’s submission. This year we submit three total unconstrained-only systems of which our best (contrastive 2) system uses last year’s best performing pre-trained language (PLM) model for ST (without cascading) and the inclusion of additional Quechua–Collao speech transcriptions found online. Fine-tuning of Microsoft’s SpeechT5 model in a ST setting along with the addition of new data and a data augmentation technique allowed us to achieve 26.7 BLEU. In this article, we present the three submissions along with a detailed description of the updated machine translation system where a comparison is done between synthetic, unconstrained, and other data for fine-tuning.</abstract>
<identifier type="citekey">e-ortega-etal-2025-quespa</identifier>
<identifier type="doi">10.18653/v1/2025.iwslt-1.25</identifier>
<location>
<url>https://aclanthology.org/2025.iwslt-1.25/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>260</start>
<end>268</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QUESPA Submission for the IWSLT 2025 Dialectal and Low-resource Speech Translation Task
%A Ortega, John E.
%A Joel Zevallos, Rodolfo
%A Chen, William
%A Abdulmumin, Idris
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Anastasopoulos, Antonis
%S Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (in-person and online)
%@ 979-8-89176-272-5
%F e-ortega-etal-2025-quespa
%X This article describes the QUESPA team speech translation (ST) submissions for the Quechua to Spanish (QUE-SPA) track featured in the Evaluation Campaign of IWSLT 2025: dialectal and low-resource speech translation. This year, there is one main submission type supported in the campaign: unconstrained. This is our third year submitting our ST systems to the IWSLT shared task and we feel that we have achieved novel performance, surpassing last year’s submission. This year we submit three total unconstrained-only systems of which our best (contrastive 2) system uses last year’s best performing pre-trained language (PLM) model for ST (without cascading) and the inclusion of additional Quechua–Collao speech transcriptions found online. Fine-tuning of Microsoft’s SpeechT5 model in a ST setting along with the addition of new data and a data augmentation technique allowed us to achieve 26.7 BLEU. In this article, we present the three submissions along with a detailed description of the updated machine translation system where a comparison is done between synthetic, unconstrained, and other data for fine-tuning.
%R 10.18653/v1/2025.iwslt-1.25
%U https://aclanthology.org/2025.iwslt-1.25/
%U https://doi.org/10.18653/v1/2025.iwslt-1.25
%P 260-268
Markdown (Informal)
[QUESPA Submission for the IWSLT 2025 Dialectal and Low-resource Speech Translation Task](https://aclanthology.org/2025.iwslt-1.25/) (Ortega et al., IWSLT 2025)
ACL