<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-ferrand-etal-2024-enenlhet">
    <titleInfo>
        <title>Enenlhet as a case-study to investigate ASR model generalizability for language documentation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Éric</namePart>
        <namePart type="family">Le Ferrand</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raina</namePart>
        <namePart type="family">Heaton</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emily</namePart>
        <namePart type="family">Prud’hommeaux</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>Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Manuel</namePart>
            <namePart type="family">Mager</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abteen</namePart>
            <namePart type="family">Ebrahimi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shruti</namePart>
            <namePart type="family">Rijhwani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Arturo</namePart>
            <namePart type="family">Oncevay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Robert</namePart>
            <namePart type="family">Pugh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Katharina</namePart>
            <namePart type="family">von der Wense</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>Although both linguists and language community members recognize the potential utility of automatic speech recognition (ASR) for documentation, one of the obstacles to using these technologies is the scarcity of data necessary to train effective systems. Recent advances in ASR, particularly the ability to fine-tune large multilingual acoustic models to small amounts of data from a new language, have demonstrated the potential of ASR for transcription. However, many proof-of-concept demonstrations of ASR in low-resource settings rely on a single data collection project, which may yield models that are biased toward that particular data scenario, whether in content, recording quality, transcription conventions, or speaker population. In this paper, we investigate the performance of two state-of-the art ASR architectures for fine-tuning acoustic models to small speech datasets with the goal of transcribing recordings of Enenlhet, an endangered Indigenous language spoken in South America. Our results suggest that while ASR offers utility for generating first-pass transcriptions of speech collected in the course of linguistic fieldwork, individual vocabulary diversity and data quality have an outsized impact on ASR accuracy.</abstract>
    <identifier type="citekey">le-ferrand-etal-2024-enenlhet</identifier>
    <identifier type="doi">10.18653/v1/2024.americasnlp-1.15</identifier>
    <location>
        <url>https://aclanthology.org/2024.americasnlp-1.15/</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>132</start>
            <end>137</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enenlhet as a case-study to investigate ASR model generalizability for language documentation
%A Le Ferrand, Éric
%A Heaton, Raina
%A Prud’hommeaux, Emily
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Rijhwani, Shruti
%Y Oncevay, Arturo
%Y Chiruzzo, Luis
%Y Pugh, Robert
%Y von der Wense, Katharina
%S Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F le-ferrand-etal-2024-enenlhet
%X Although both linguists and language community members recognize the potential utility of automatic speech recognition (ASR) for documentation, one of the obstacles to using these technologies is the scarcity of data necessary to train effective systems. Recent advances in ASR, particularly the ability to fine-tune large multilingual acoustic models to small amounts of data from a new language, have demonstrated the potential of ASR for transcription. However, many proof-of-concept demonstrations of ASR in low-resource settings rely on a single data collection project, which may yield models that are biased toward that particular data scenario, whether in content, recording quality, transcription conventions, or speaker population. In this paper, we investigate the performance of two state-of-the art ASR architectures for fine-tuning acoustic models to small speech datasets with the goal of transcribing recordings of Enenlhet, an endangered Indigenous language spoken in South America. Our results suggest that while ASR offers utility for generating first-pass transcriptions of speech collected in the course of linguistic fieldwork, individual vocabulary diversity and data quality have an outsized impact on ASR accuracy.
%R 10.18653/v1/2024.americasnlp-1.15
%U https://aclanthology.org/2024.americasnlp-1.15/
%U https://doi.org/10.18653/v1/2024.americasnlp-1.15
%P 132-137

Markdown (Informal)

[Enenlhet as a case-study to investigate ASR model generalizability for language documentation](https://aclanthology.org/2024.americasnlp-1.15/) (Le Ferrand et al., AmericasNLP 2024)

• Enenlhet as a case-study to investigate ASR model generalizability for language documentation (Le Ferrand et al., AmericasNLP 2024)

ACL

• Éric Le Ferrand, Raina Heaton, and Emily Prud’hommeaux. 2024. Enenlhet as a case-study to investigate ASR model generalizability for language documentation. In Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024), pages 132–137, Mexico City, Mexico. Association for Computational Linguistics.