@inproceedings{zevallos-etal-2026-cateng,
title = "{CATENG} Submission for the {IWSLT} 2026: Dialectal and Low-resource Speech Translation Task",
author = "Zevallos, Rodolfo Joel and
Casals, Marc and
Ortega, John E. and
Carraro, Fabr{\'i}cio and
Buitrago, Pol and
C{\'a}mbara, Guillermo",
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-1.18/",
pages = "164--170",
ISBN = "979-8-89176-411-8",
abstract = "We present the CATENG systems submitted to the IWSLT 2026 Dialectal and Low-Resource Speech Translation shared task for the Catalan{--}English (CA{--}EN) pair. Although Catalan is not strictly low-resource, its dialectal diversity and relative under-representation in speech technology make it a challenging setting. We evaluate three unconstrained systems: two cascaded approaches combining ASR and MT, and one end-to-end model. Our primary system uses a Mamba-based ASR (ConMamba) with a fine-tuned NLLB-200 MT model, while a contrastive system replaces the ASR with Whisper-v3; we also evaluate an end-to-end SpeechT5 model with data augmentation. Experiments are conducted on the IWSLT 2026 Catalan dataset (15 hours), complemented with large-scale parallel text. Results show that cascaded systems outperform end-to-end ST, with Whisper-v3 + NLLB achieving 44.7 BLEU and 65.1 chrF. We find that performance is primarily constrained by ASR quality rather than MT capacity, and that Mamba-based ASR models provide competitive results, highlighting the importance of robust speech representations and dialectal coverage for Catalan{--}English speech translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zevallos-etal-2026-cateng">
<titleInfo>
<title>CATENG Submission for the IWSLT 2026: Dialectal and Low-resource Speech Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rodolfo</namePart>
<namePart type="given">Joel</namePart>
<namePart type="family">Zevallos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Casals</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Fabrício</namePart>
<namePart type="family">Carraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pol</namePart>
<namePart type="family">Buitrago</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Cámbara</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>We present the CATENG systems submitted to the IWSLT 2026 Dialectal and Low-Resource Speech Translation shared task for the Catalan–English (CA–EN) pair. Although Catalan is not strictly low-resource, its dialectal diversity and relative under-representation in speech technology make it a challenging setting. We evaluate three unconstrained systems: two cascaded approaches combining ASR and MT, and one end-to-end model. Our primary system uses a Mamba-based ASR (ConMamba) with a fine-tuned NLLB-200 MT model, while a contrastive system replaces the ASR with Whisper-v3; we also evaluate an end-to-end SpeechT5 model with data augmentation. Experiments are conducted on the IWSLT 2026 Catalan dataset (15 hours), complemented with large-scale parallel text. Results show that cascaded systems outperform end-to-end ST, with Whisper-v3 + NLLB achieving 44.7 BLEU and 65.1 chrF. We find that performance is primarily constrained by ASR quality rather than MT capacity, and that Mamba-based ASR models provide competitive results, highlighting the importance of robust speech representations and dialectal coverage for Catalan–English speech translation.</abstract>
<identifier type="citekey">zevallos-etal-2026-cateng</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.18/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>164</start>
<end>170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CATENG Submission for the IWSLT 2026: Dialectal and Low-resource Speech Translation Task
%A Zevallos, Rodolfo Joel
%A Casals, Marc
%A Ortega, John E.
%A Carraro, Fabrício
%A Buitrago, Pol
%A Cámbara, Guillermo
%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 zevallos-etal-2026-cateng
%X We present the CATENG systems submitted to the IWSLT 2026 Dialectal and Low-Resource Speech Translation shared task for the Catalan–English (CA–EN) pair. Although Catalan is not strictly low-resource, its dialectal diversity and relative under-representation in speech technology make it a challenging setting. We evaluate three unconstrained systems: two cascaded approaches combining ASR and MT, and one end-to-end model. Our primary system uses a Mamba-based ASR (ConMamba) with a fine-tuned NLLB-200 MT model, while a contrastive system replaces the ASR with Whisper-v3; we also evaluate an end-to-end SpeechT5 model with data augmentation. Experiments are conducted on the IWSLT 2026 Catalan dataset (15 hours), complemented with large-scale parallel text. Results show that cascaded systems outperform end-to-end ST, with Whisper-v3 + NLLB achieving 44.7 BLEU and 65.1 chrF. We find that performance is primarily constrained by ASR quality rather than MT capacity, and that Mamba-based ASR models provide competitive results, highlighting the importance of robust speech representations and dialectal coverage for Catalan–English speech translation.
%U https://aclanthology.org/2026.iwslt-1.18/
%P 164-170
Markdown (Informal)
[CATENG Submission for the IWSLT 2026: Dialectal and Low-resource Speech Translation Task](https://aclanthology.org/2026.iwslt-1.18/) (Zevallos et al., IWSLT 2026)
ACL