<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="danilevskyi-etal-2026-addressing">
    <titleInfo>
        <title>Addressing Accent Disparities in Automatic Speech Recognition: A Comparative Study of Single and Two-Step Adaptation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mykhailo</namePart>
        <namePart type="family">Danilevskyi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fernando</namePart>
        <namePart type="family">Perez-Tellez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jelena</namePart>
        <namePart type="family">Vasic</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>Automatic speech recognition (ASR) systems often exhibit uneven performance across accents, raising concerns about fairness and bias. This study investigates the impact of model fine-tuning strategies on ASR performance and accent-related disparities. We conduct a controlled empirical evaluation of two adaptation approaches—single-step and two-step fine-tuning—using pretrained Whisper (small) and Wav2Vec2-XLSR-53 models on African-accented English speech from the AfriSpeech-200 dataset, covering Yoruba, Igbo, Swahili, and Hausa accents. Both fine-tuning strategies substantially reduced mean word error rate (WER) for all models. However, these improvements did not translate into consistent reductions in accent-related performance gaps. When analysed separately across general and clinical subsets, WER gaps often increased due to uneven gains across accents. Although two-step fine-tuning provided modest improvements over single-step adaptation, its impact on reducing disparities remained limited. These findings indicate that fine-tuning primarily optimises performance without effectively addressing systematic bias across speaker groups, even when models are specialised for individual accents. This highlights the limitations of per-accent specialisation as a practical bias mitigation strategy.</abstract>
    <identifier type="citekey">danilevskyi-etal-2026-addressing</identifier>
    <identifier type="doi">10.63317/3zjiz9fsk4fy</identifier>
    <location>
        <url>https://aclanthology.org/2026.speakable-1.9/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>79</start>
            <end>85</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Addressing Accent Disparities in Automatic Speech Recognition: A Comparative Study of Single and Two-Step Adaptation
%A Danilevskyi, Mykhailo
%A Perez-Tellez, Fernando
%A Vasic, Jelena
%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 danilevskyi-etal-2026-addressing
%X Automatic speech recognition (ASR) systems often exhibit uneven performance across accents, raising concerns about fairness and bias. This study investigates the impact of model fine-tuning strategies on ASR performance and accent-related disparities. We conduct a controlled empirical evaluation of two adaptation approaches—single-step and two-step fine-tuning—using pretrained Whisper (small) and Wav2Vec2-XLSR-53 models on African-accented English speech from the AfriSpeech-200 dataset, covering Yoruba, Igbo, Swahili, and Hausa accents. Both fine-tuning strategies substantially reduced mean word error rate (WER) for all models. However, these improvements did not translate into consistent reductions in accent-related performance gaps. When analysed separately across general and clinical subsets, WER gaps often increased due to uneven gains across accents. Although two-step fine-tuning provided modest improvements over single-step adaptation, its impact on reducing disparities remained limited. These findings indicate that fine-tuning primarily optimises performance without effectively addressing systematic bias across speaker groups, even when models are specialised for individual accents. This highlights the limitations of per-accent specialisation as a practical bias mitigation strategy.
%R 10.63317/3zjiz9fsk4fy
%U https://aclanthology.org/2026.speakable-1.9/
%U https://doi.org/10.63317/3zjiz9fsk4fy
%P 79-85

Markdown (Informal)

[Addressing Accent Disparities in Automatic Speech Recognition: A Comparative Study of Single and Two-Step Adaptation](https://aclanthology.org/2026.speakable-1.9/) (Danilevskyi et al., SPEAKABLE 2026)

• Addressing Accent Disparities in Automatic Speech Recognition: A Comparative Study of Single and Two-Step Adaptation (Danilevskyi et al., SPEAKABLE 2026)

ACL

• Mykhailo Danilevskyi, Fernando Perez-Tellez, and Jelena Vasic. 2026. Addressing Accent Disparities in Automatic Speech Recognition: A Comparative Study of Single and Two-Step Adaptation. In Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026, pages 79–85, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).