<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rykova-etal-2025-enhancing">
    <titleInfo>
        <title>Enhancing ASR-based error analysis for atypical speech: post hoc integration of aphasic and dialectal phonetic features</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Eugenia</namePart>
        <namePart type="family">Rykova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Elisabeth</namePart>
        <namePart type="family">Zeuner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Susanne</namePart>
        <namePart type="family">Voigt-Zimmermann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mathias</namePart>
        <namePart type="family">Walther</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Journal for Language Technology and Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>German Society for Computational Linguistics and Language Technology</publisher>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Despite current progress, automatic speech recognition (ASR) often struggles with non-standard speech, for example, influenced by dialectal or pathological features. (Re)training ASR models to accommodate these variations is not always possible due to limited data. This paper proposes applying the knowledge about non-standard (aphasic and dialectal) phonetic features to the ASR transcription post hoc. Using speech data from German speakers with aphasia who speak the Thuringian-Upper Saxon dialect, this study evaluates the impact of these modifications on an ASR-based error analysis pipeline. The approach helps to reduce automatic error rates on the recordings manually labelled as error-free. The performance of the pipeline also improves both in general acceptance or rejection of the responses and error attribution. General acceptance/rejection accuracy reaches the mean of 83.3%, which is considered sufficient to be used in a digital application for speech and language therapy support.</abstract>
    <identifier type="citekey">rykova-etal-2025-enhancing</identifier>
    <identifier type="doi">10.21248/jlcl.38.2025.251</identifier>
    <location>
        <url>https://aclanthology.org/2025.jlcl-1.3/</url>
    </location>
    <part>
        <date>2025-12</date>
        <detail type="volume"><number>38</number></detail>
        <detail type="issue"><number>1</number></detail>
        <extent unit="page">
            <start>37</start>
            <end>62</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Enhancing ASR-based error analysis for atypical speech: post hoc integration of aphasic and dialectal phonetic features
%A Rykova, Eugenia
%A Zeuner, Elisabeth
%A Voigt-Zimmermann, Susanne
%A Walther, Mathias
%J Journal for Language Technology and Computational Linguistics
%D 2025
%8 December
%V 38
%N 1
%I German Society for Computational Linguistics and Language Technology
%F rykova-etal-2025-enhancing
%X Despite current progress, automatic speech recognition (ASR) often struggles with non-standard speech, for example, influenced by dialectal or pathological features. (Re)training ASR models to accommodate these variations is not always possible due to limited data. This paper proposes applying the knowledge about non-standard (aphasic and dialectal) phonetic features to the ASR transcription post hoc. Using speech data from German speakers with aphasia who speak the Thuringian-Upper Saxon dialect, this study evaluates the impact of these modifications on an ASR-based error analysis pipeline. The approach helps to reduce automatic error rates on the recordings manually labelled as error-free. The performance of the pipeline also improves both in general acceptance or rejection of the responses and error attribution. General acceptance/rejection accuracy reaches the mean of 83.3%, which is considered sufficient to be used in a digital application for speech and language therapy support.
%R 10.21248/jlcl.38.2025.251
%U https://aclanthology.org/2025.jlcl-1.3/
%U https://doi.org/10.21248/jlcl.38.2025.251
%P 37-62

Markdown (Informal)

[Enhancing ASR-based error analysis for atypical speech: post hoc integration of aphasic and dialectal phonetic features](https://aclanthology.org/2025.jlcl-1.3/) (Rykova et al., JLCL 2025)

• Enhancing ASR-based error analysis for atypical speech: post hoc integration of aphasic and dialectal phonetic features (Rykova et al., JLCL 2025)

ACL

• Eugenia Rykova, Elisabeth Zeuner, Susanne Voigt-Zimmermann, and Mathias Walther. 2025. Enhancing ASR-based error analysis for atypical speech: post hoc integration of aphasic and dialectal phonetic features. Journal for Language Technology and Computational Linguistics, 38(1):37–62.