@inproceedings{lee-etal-2025-speech,
title = "Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection",
author = "Lee, Beomseok and
Gaido, Marco and
Calapodescu, Ioan and
Besacier, Laurent and
Negri, Matteo",
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.455/",
pages = "6816--6826",
abstract = "While crowdsourcing is an established solution for facilitating and scaling the collection of speech data, the involvement of non-experts necessitates protocols to ensure final data quality. To reduce the costs of these essential controls, this paper investigates the use of Speech Foundation Models (SFMs) to automate the validation process, examining for the first time the cost/quality trade-off in data acquisition. Experiments conducted on French, German, and Korean data demonstrate that SFM-based validation has the potential to reduce reliance on human validation, resulting in an estimated cost saving of over 40.0{\%} without degrading final data quality. These findings open new opportunities for more efficient, cost-effective, and scalable speech data acquisition."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2025-speech">
<titleInfo>
<title>Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beomseok</namePart>
<namePart type="family">Lee</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">Ioan</namePart>
<namePart type="family">Calapodescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</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>
<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>While crowdsourcing is an established solution for facilitating and scaling the collection of speech data, the involvement of non-experts necessitates protocols to ensure final data quality. To reduce the costs of these essential controls, this paper investigates the use of Speech Foundation Models (SFMs) to automate the validation process, examining for the first time the cost/quality trade-off in data acquisition. Experiments conducted on French, German, and Korean data demonstrate that SFM-based validation has the potential to reduce reliance on human validation, resulting in an estimated cost saving of over 40.0% without degrading final data quality. These findings open new opportunities for more efficient, cost-effective, and scalable speech data acquisition.</abstract>
<identifier type="citekey">lee-etal-2025-speech</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.455/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>6816</start>
<end>6826</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection
%A Lee, Beomseok
%A Gaido, Marco
%A Calapodescu, Ioan
%A Besacier, Laurent
%A Negri, Matteo
%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 lee-etal-2025-speech
%X While crowdsourcing is an established solution for facilitating and scaling the collection of speech data, the involvement of non-experts necessitates protocols to ensure final data quality. To reduce the costs of these essential controls, this paper investigates the use of Speech Foundation Models (SFMs) to automate the validation process, examining for the first time the cost/quality trade-off in data acquisition. Experiments conducted on French, German, and Korean data demonstrate that SFM-based validation has the potential to reduce reliance on human validation, resulting in an estimated cost saving of over 40.0% without degrading final data quality. These findings open new opportunities for more efficient, cost-effective, and scalable speech data acquisition.
%U https://aclanthology.org/2025.coling-main.455/
%P 6816-6826
Markdown (Informal)
[Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection](https://aclanthology.org/2025.coling-main.455/) (Lee et al., COLING 2025)
ACL