<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fedchenko-jordan-2026-leveraging">
    <titleInfo>
        <title>Leveraging Linguistic Similarity for Low-Resource Speech Transcription</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Valentina</namePart>
        <namePart type="family">Fedchenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eric</namePart>
        <namePart type="family">Jordan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This study investigates how large-scale, self-supervised acoustic models (like XLSR and MMS) represent linguistic similarity and whether this can optimize Automatic Speech Recognition (ASR) for low-resource and dialectally diverse languages. While these models excel at cross-lingual transfer learning, their internal representations of fine-grained dialectal variation remain opaque. We focus on Yiddish, a language with a complex dialect continuum, to test if a model’s internal acoustic similarity metric—Acoustic Token Distribution Similarity (ATDS)—predicts ASR performance. Our methodology involved fine-tuning models on Yiddish dialects and measuring ATDS between Yiddish and related languages. Results confirm that ATDS is a meaningful predictor: higher acoustic similarity in the model’s latent space correlates with lower character error rates (CER) after fine-tuning. This relationship is strongest in mid-to-upper layers of the MMS model and for in-domain data. Crucially, ATDS captures model-dependent acoustic similarity, which does not always align with genealogical linguistic relationships but remains a practical indicator of transfer learning potential. We conclude that ATDS is a valuable tool for selecting donor languages to develop more efficient, dialect-sensitive ASR systems for language documentation, even if its absolute values require careful interpretation against linguistic knowledge.</abstract>
    <identifier type="citekey">fedchenko-jordan-2026-leveraging</identifier>
    <identifier type="doi">10.63317/5mcp4ektu7mw</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.288/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>3590</start>
            <end>3598</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Leveraging Linguistic Similarity for Low-Resource Speech Transcription
%A Fedchenko, Valentina
%A Jordan, Eric
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F fedchenko-jordan-2026-leveraging
%X This study investigates how large-scale, self-supervised acoustic models (like XLSR and MMS) represent linguistic similarity and whether this can optimize Automatic Speech Recognition (ASR) for low-resource and dialectally diverse languages. While these models excel at cross-lingual transfer learning, their internal representations of fine-grained dialectal variation remain opaque. We focus on Yiddish, a language with a complex dialect continuum, to test if a model’s internal acoustic similarity metric—Acoustic Token Distribution Similarity (ATDS)—predicts ASR performance. Our methodology involved fine-tuning models on Yiddish dialects and measuring ATDS between Yiddish and related languages. Results confirm that ATDS is a meaningful predictor: higher acoustic similarity in the model’s latent space correlates with lower character error rates (CER) after fine-tuning. This relationship is strongest in mid-to-upper layers of the MMS model and for in-domain data. Crucially, ATDS captures model-dependent acoustic similarity, which does not always align with genealogical linguistic relationships but remains a practical indicator of transfer learning potential. We conclude that ATDS is a valuable tool for selecting donor languages to develop more efficient, dialect-sensitive ASR systems for language documentation, even if its absolute values require careful interpretation against linguistic knowledge.
%R 10.63317/5mcp4ektu7mw
%U https://aclanthology.org/2026.lrec-1.288/
%U https://doi.org/10.63317/5mcp4ektu7mw
%P 3590-3598

Markdown (Informal)

[Leveraging Linguistic Similarity for Low-Resource Speech Transcription](https://aclanthology.org/2026.lrec-1.288/) (Fedchenko & Jordan, LREC 2026)

• Leveraging Linguistic Similarity for Low-Resource Speech Transcription (Fedchenko & Jordan, LREC 2026)

ACL

• Valentina Fedchenko and Eric Jordan. 2026. Leveraging Linguistic Similarity for Low-Resource Speech Transcription. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3590–3598, Palma de Mallorca, Spain. ELRA Language Resource Association.