<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asakawa-etal-2026-adaptive">
    <titleInfo>
        <title>Adaptive Method for Self-Supervised Learning Models on Automatic Dialect Speech Recognition Based on Shared Knowledge of Japanese Dialects and Standard Japanese</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Naoru</namePart>
        <namePart type="family">Asakawa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Naoki</namePart>
        <namePart type="family">Takahashi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Atsuhiko</namePart>
        <namePart type="family">Kai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seiichi</namePart>
        <namePart type="family">Nakagawa</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>Speech recognition for Japanese dialects is challenging, and recognition accuracy tends to be lower compared to standard Japanese. Previous research proposed a three-step learning method based on the self-supervised learning (SSL) model XLS-R as the base model, incorporating three multi-task learning tasks: SSL, ASR, and dialect identification (DID). While this achieved improved recognition performance for dialect speech, it faced the issue of degraded recognition performance for standard Japanese. This study proposes an adaptation method to construct a single speech recognition model, based on the prior model, that is suitable for both Japanese dialects and standard Japanese. We explored the use of diverse speech corpora, including ReazonSpeech based on TV broadcast audio and CEJC based on everyday conversational speech, in addition to the standard Japanese speech corpus CSJ and the dialect speech corpus COJADS used in prior research, aiming for knowledge sharing between dialects and standard Japanese. As a result, we confirmed improved recognition performance for both dialects and standard Japanese by including both in the final step of a three-step learning method. We also examined the impact of differences in corpus type and domain on recognition performance.</abstract>
    <identifier type="citekey">asakawa-etal-2026-adaptive</identifier>
    <identifier type="doi">10.63317/2tb4unmnwikb</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.285/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>3556</start>
            <end>3565</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Adaptive Method for Self-Supervised Learning Models on Automatic Dialect Speech Recognition Based on Shared Knowledge of Japanese Dialects and Standard Japanese
%A Asakawa, Naoru
%A Takahashi, Naoki
%A Kai, Atsuhiko
%A Nakagawa, Seiichi
%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 asakawa-etal-2026-adaptive
%X Speech recognition for Japanese dialects is challenging, and recognition accuracy tends to be lower compared to standard Japanese. Previous research proposed a three-step learning method based on the self-supervised learning (SSL) model XLS-R as the base model, incorporating three multi-task learning tasks: SSL, ASR, and dialect identification (DID). While this achieved improved recognition performance for dialect speech, it faced the issue of degraded recognition performance for standard Japanese. This study proposes an adaptation method to construct a single speech recognition model, based on the prior model, that is suitable for both Japanese dialects and standard Japanese. We explored the use of diverse speech corpora, including ReazonSpeech based on TV broadcast audio and CEJC based on everyday conversational speech, in addition to the standard Japanese speech corpus CSJ and the dialect speech corpus COJADS used in prior research, aiming for knowledge sharing between dialects and standard Japanese. As a result, we confirmed improved recognition performance for both dialects and standard Japanese by including both in the final step of a three-step learning method. We also examined the impact of differences in corpus type and domain on recognition performance.
%R 10.63317/2tb4unmnwikb
%U https://aclanthology.org/2026.lrec-1.285/
%U https://doi.org/10.63317/2tb4unmnwikb
%P 3556-3565

Markdown (Informal)

[Adaptive Method for Self-Supervised Learning Models on Automatic Dialect Speech Recognition Based on Shared Knowledge of Japanese Dialects and Standard Japanese](https://aclanthology.org/2026.lrec-1.285/) (Asakawa et al., LREC 2026)

• Adaptive Method for Self-Supervised Learning Models on Automatic Dialect Speech Recognition Based on Shared Knowledge of Japanese Dialects and Standard Japanese (Asakawa et al., LREC 2026)

ACL

• Naoru Asakawa, Naoki Takahashi, Atsuhiko Kai, and Seiichi Nakagawa. 2026. Adaptive Method for Self-Supervised Learning Models on Automatic Dialect Speech Recognition Based on Shared Knowledge of Japanese Dialects and Standard Japanese. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3556–3565, Palma de Mallorca, Spain. ELRA Language Resource Association.