@inproceedings{avila-crego-2025-leveraging,
title = "Leveraging Large Pre-trained Multilingual Models for High-Quality Speech-to-Text Translation on Industry Scenarios",
author = "Avila, Marko and
Crego, Josep",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.509/",
pages = "7624--7633",
abstract = "Speech-to-Text Translation (S2TT) involves converting spoken language from a source language directly into text in a target language. Traditionally, S2TT systems rely on a sequential pipeline that combines Automatic Speech Recognition (ASR) and Machine Translation (MT) models. However, these systems are prone to error propagation and demand substantial resources to develop and train each component independently. Thus, posing a major challenge in industry settings where cost-effective yet highly accurate S2TT solutions are essential. With the increasing availability of multilingual large pre-trained speech models (LPSM), we propose a parameter-efficient framework that integrates one LPSM with a multilingual MT engine. We evaluate the effectiveness of several well-established LPSMs within this framework, focusing on a real-world industry scenario that involves building a system capable of translating between French, English, and Arabic. The results show that high-quality S2TT systems can be built with minimal computational resources, offering an efficient solution for cross-lingual communication."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="avila-crego-2025-leveraging">
<titleInfo>
<title>Leveraging Large Pre-trained Multilingual Models for High-Quality Speech-to-Text Translation on Industry Scenarios</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Avila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="family">Crego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech-to-Text Translation (S2TT) involves converting spoken language from a source language directly into text in a target language. Traditionally, S2TT systems rely on a sequential pipeline that combines Automatic Speech Recognition (ASR) and Machine Translation (MT) models. However, these systems are prone to error propagation and demand substantial resources to develop and train each component independently. Thus, posing a major challenge in industry settings where cost-effective yet highly accurate S2TT solutions are essential. With the increasing availability of multilingual large pre-trained speech models (LPSM), we propose a parameter-efficient framework that integrates one LPSM with a multilingual MT engine. We evaluate the effectiveness of several well-established LPSMs within this framework, focusing on a real-world industry scenario that involves building a system capable of translating between French, English, and Arabic. The results show that high-quality S2TT systems can be built with minimal computational resources, offering an efficient solution for cross-lingual communication.</abstract>
<identifier type="citekey">avila-crego-2025-leveraging</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.509/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>7624</start>
<end>7633</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Large Pre-trained Multilingual Models for High-Quality Speech-to-Text Translation on Industry Scenarios
%A Avila, Marko
%A Crego, Josep
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F avila-crego-2025-leveraging
%X Speech-to-Text Translation (S2TT) involves converting spoken language from a source language directly into text in a target language. Traditionally, S2TT systems rely on a sequential pipeline that combines Automatic Speech Recognition (ASR) and Machine Translation (MT) models. However, these systems are prone to error propagation and demand substantial resources to develop and train each component independently. Thus, posing a major challenge in industry settings where cost-effective yet highly accurate S2TT solutions are essential. With the increasing availability of multilingual large pre-trained speech models (LPSM), we propose a parameter-efficient framework that integrates one LPSM with a multilingual MT engine. We evaluate the effectiveness of several well-established LPSMs within this framework, focusing on a real-world industry scenario that involves building a system capable of translating between French, English, and Arabic. The results show that high-quality S2TT systems can be built with minimal computational resources, offering an efficient solution for cross-lingual communication.
%U https://aclanthology.org/2025.coling-main.509/
%P 7624-7633
Markdown (Informal)
[Leveraging Large Pre-trained Multilingual Models for High-Quality Speech-to-Text Translation on Industry Scenarios](https://aclanthology.org/2025.coling-main.509/) (Avila & Crego, COLING 2025)
ACL