<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fily-etal-2026-investigating">
    <titleInfo>
        <title>Investigating Speaker Pronunciation Variability in Speech Embeddings: Speaker and L1 Effects on French as a Second Language</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maxime</namePart>
        <namePart type="family">Fily</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martine</namePart>
        <namePart type="family">Adda-Decker</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guillaume</namePart>
        <namePart type="family">Wisniewski</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 Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nina</namePart>
            <namePart type="family">Hosseini-Kivanani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alessio</namePart>
            <namePart type="family">Brutti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marco</namePart>
            <namePart type="family">Matassoni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sandipana</namePart>
            <namePart type="family">Dowerah</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Davide</namePart>
            <namePart type="family">Liga</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christoph</namePart>
            <namePart type="family">Schommer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Speech variation between native and non-native speakers of French is addressed with a low-resource method based on a frame-wise comparison of wav2vec2 acoustic embeddings, using fine-grained phonetic transcriptions by expert annotators as baseline. z-normalisation and t-normalisation are explored to assess what the embeddings contain in terms of phonetically analysable information. We explore non-supervised methods for solving basic speech-related research questions. Adapting Dynamic Time Warping to speech embeddings, we compare phonologically similar recordings of sentences read-aloud by native vs. non-native speakers of French. The question is whether XLSR-53 embeddings are more robust than MFCCs to inter-speaker vs. intra-speaker variability for same words. Then we investigate whether native speaker productions are more stable than those of non-native speakers. Results suggest that the model allows phonetically meaningful correlative analyses. Working on the raw embeddings shows however that the representations are not speaker-independent, so with a view to address issues in relationship with L2 pronunciation variability, we show that t-normalisation brings us a way to separate fluency and accuracy effects in L2-speech. This shows that wav2vec2 encapsulates time-dependent phonetic information in the embeddings, including speaker accent which can not easily be disentangled from speaker ID.</abstract>
    <identifier type="citekey">fily-etal-2026-investigating</identifier>
    <identifier type="doi">10.63317/4abhhjss97b8</identifier>
    <location>
        <url>https://aclanthology.org/2026.speakable-1.10/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>86</start>
            <end>97</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Investigating Speaker Pronunciation Variability in Speech Embeddings: Speaker and L1 Effects on French as a Second Language
%A Fily, Maxime
%A Adda-Decker, Martine
%A Wisniewski, Guillaume
%Y Hosseini-Kivanani, Nina
%Y Brutti, Alessio
%Y Matassoni, Marco
%Y Dowerah, Sandipana
%Y Liga, Davide
%Y Schommer, Christoph
%S Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F fily-etal-2026-investigating
%X Speech variation between native and non-native speakers of French is addressed with a low-resource method based on a frame-wise comparison of wav2vec2 acoustic embeddings, using fine-grained phonetic transcriptions by expert annotators as baseline. z-normalisation and t-normalisation are explored to assess what the embeddings contain in terms of phonetically analysable information. We explore non-supervised methods for solving basic speech-related research questions. Adapting Dynamic Time Warping to speech embeddings, we compare phonologically similar recordings of sentences read-aloud by native vs. non-native speakers of French. The question is whether XLSR-53 embeddings are more robust than MFCCs to inter-speaker vs. intra-speaker variability for same words. Then we investigate whether native speaker productions are more stable than those of non-native speakers. Results suggest that the model allows phonetically meaningful correlative analyses. Working on the raw embeddings shows however that the representations are not speaker-independent, so with a view to address issues in relationship with L2 pronunciation variability, we show that t-normalisation brings us a way to separate fluency and accuracy effects in L2-speech. This shows that wav2vec2 encapsulates time-dependent phonetic information in the embeddings, including speaker accent which can not easily be disentangled from speaker ID.
%R 10.63317/4abhhjss97b8
%U https://aclanthology.org/2026.speakable-1.10/
%U https://doi.org/10.63317/4abhhjss97b8
%P 86-97

Markdown (Informal)

[Investigating Speaker Pronunciation Variability in Speech Embeddings: Speaker and L1 Effects on French as a Second Language](https://aclanthology.org/2026.speakable-1.10/) (Fily et al., SPEAKABLE 2026)

• Investigating Speaker Pronunciation Variability in Speech Embeddings: Speaker and L1 Effects on French as a Second Language (Fily et al., SPEAKABLE 2026)

ACL

• Maxime Fily, Martine Adda-Decker, and Guillaume Wisniewski. 2026. Investigating Speaker Pronunciation Variability in Speech Embeddings: Speaker and L1 Effects on French as a Second Language. In Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026, pages 86–97, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).