@inproceedings{zee-etal-2024-group,
title = "Group Fairness in Multilingual Speech Recognition Models",
author = "Zee, Anna and
Zee, Marc and
S{\o}gaard, Anders",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.143",
pages = "2213--2226",
abstract = "We evaluate the performance disparity of the Whisper and MMS families of ASR models across the VoxPopuli and Common Voice multilingual datasets, with an eye toward intersectionality. Our two most important findings are that model size, surprisingly, correlates logarithmically with worst-case performance disparities, meaning that larger (and better) models are less fair. We also observe the importance of intersectionality. In particular, models often exhibit significant performance disparity across binary gender for adolescents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zee-etal-2024-group">
<titleInfo>
<title>Group Fairness in Multilingual Speech Recognition Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Zee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Zee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We evaluate the performance disparity of the Whisper and MMS families of ASR models across the VoxPopuli and Common Voice multilingual datasets, with an eye toward intersectionality. Our two most important findings are that model size, surprisingly, correlates logarithmically with worst-case performance disparities, meaning that larger (and better) models are less fair. We also observe the importance of intersectionality. In particular, models often exhibit significant performance disparity across binary gender for adolescents.</abstract>
<identifier type="citekey">zee-etal-2024-group</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.143</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>2213</start>
<end>2226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Group Fairness in Multilingual Speech Recognition Models
%A Zee, Anna
%A Zee, Marc
%A Søgaard, Anders
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zee-etal-2024-group
%X We evaluate the performance disparity of the Whisper and MMS families of ASR models across the VoxPopuli and Common Voice multilingual datasets, with an eye toward intersectionality. Our two most important findings are that model size, surprisingly, correlates logarithmically with worst-case performance disparities, meaning that larger (and better) models are less fair. We also observe the importance of intersectionality. In particular, models often exhibit significant performance disparity across binary gender for adolescents.
%U https://aclanthology.org/2024.findings-naacl.143
%P 2213-2226
Markdown (Informal)
[Group Fairness in Multilingual Speech Recognition Models](https://aclanthology.org/2024.findings-naacl.143) (Zee et al., Findings 2024)
ACL