@inproceedings{meyer-etal-2020-artie,
title = "Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications",
author = "Meyer, Josh and
Rauchenstein, Lindy and
Eisenberg, Joshua D. and
Howell, Nicholas",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.796",
pages = "6462--6468",
abstract = "We describe the creation of the Artie Bias Corpus, an English dataset of expert-validated {\textless}audio, transcript{\textgreater} pairs with demographic tags for age, gender, accent. We also release open software which may be used with the Artie Bias Corpus to detect demographic bias in Automatic Speech Recognition systems, and can be extended to other speech technologies. The Artie Bias Corpus is a curated subset of the Mozilla Common Voice corpus, which we release under a Creative Commons CC0 license {--} the most open and permissive license for data. This article contains information on the criteria used to select and annotate the Artie Bias Corpus in addition to experiments in which we detect and attempt to mitigate bias in end-to-end speech recognition models. We we observe a significant accent bias in our baseline DeepSpeech model, with more accurate transcriptions of US English compared to Indian English. We do not, however, find evidence for a significant gender bias. We then show significant improvements on individual demographic groups from fine-tuning.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meyer-etal-2020-artie">
<titleInfo>
<title>Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Meyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lindy</namePart>
<namePart type="family">Rauchenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Eisenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Howell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We describe the creation of the Artie Bias Corpus, an English dataset of expert-validated \textlessaudio, transcript\textgreater pairs with demographic tags for age, gender, accent. We also release open software which may be used with the Artie Bias Corpus to detect demographic bias in Automatic Speech Recognition systems, and can be extended to other speech technologies. The Artie Bias Corpus is a curated subset of the Mozilla Common Voice corpus, which we release under a Creative Commons CC0 license – the most open and permissive license for data. This article contains information on the criteria used to select and annotate the Artie Bias Corpus in addition to experiments in which we detect and attempt to mitigate bias in end-to-end speech recognition models. We we observe a significant accent bias in our baseline DeepSpeech model, with more accurate transcriptions of US English compared to Indian English. We do not, however, find evidence for a significant gender bias. We then show significant improvements on individual demographic groups from fine-tuning.</abstract>
<identifier type="citekey">meyer-etal-2020-artie</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.796</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6462</start>
<end>6468</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications
%A Meyer, Josh
%A Rauchenstein, Lindy
%A Eisenberg, Joshua D.
%A Howell, Nicholas
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F meyer-etal-2020-artie
%X We describe the creation of the Artie Bias Corpus, an English dataset of expert-validated \textlessaudio, transcript\textgreater pairs with demographic tags for age, gender, accent. We also release open software which may be used with the Artie Bias Corpus to detect demographic bias in Automatic Speech Recognition systems, and can be extended to other speech technologies. The Artie Bias Corpus is a curated subset of the Mozilla Common Voice corpus, which we release under a Creative Commons CC0 license – the most open and permissive license for data. This article contains information on the criteria used to select and annotate the Artie Bias Corpus in addition to experiments in which we detect and attempt to mitigate bias in end-to-end speech recognition models. We we observe a significant accent bias in our baseline DeepSpeech model, with more accurate transcriptions of US English compared to Indian English. We do not, however, find evidence for a significant gender bias. We then show significant improvements on individual demographic groups from fine-tuning.
%U https://aclanthology.org/2020.lrec-1.796
%P 6462-6468
Markdown (Informal)
[Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications](https://aclanthology.org/2020.lrec-1.796) (Meyer et al., LREC 2020)
ACL