@inproceedings{fabre-etal-2026-building,
title = "Building a Dataset for {F}rench Accent Classification Evaluation: Are We There Yet?",
author = "Fabre, Diandra and
Avanzi, Mathieu and
Portet, Fran{\c{c}}ois",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.450/",
doi = "10.63317/5ayaxbnxjfen",
pages = "5711--5721",
abstract = "Current evaluation practices in speech processing systems often overlook the diversity of spoken accents, leading to significant performance disparities across speaker groups. This issue largely comes from biases and imbalances in training corpora, and is further compounded by the scarcity of open-source datasets suitable for evaluating accent variability in French. To address this gap, we extend the CFPR dataset with explicit accent labels, providing a new benchmark for assessing the robustness of speech technology systems across diverse French accents. We additionally conduct a perceptual study with 87 human participants to evaluate the reliability and interpretability of these labels. Using this resource, we evaluated an eight-class French accent classifier trained on Common Voice data. The first results highlight both the complexity of automatic French accent recognition in low-resource settings, and the difficulty for French-speakers to perceive all the linguistic variabilities in French-speaking countries."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fabre-etal-2026-building">
<titleInfo>
<title>Building a Dataset for French Accent Classification Evaluation: Are We There Yet?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diandra</namePart>
<namePart type="family">Fabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Avanzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Portet</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>Current evaluation practices in speech processing systems often overlook the diversity of spoken accents, leading to significant performance disparities across speaker groups. This issue largely comes from biases and imbalances in training corpora, and is further compounded by the scarcity of open-source datasets suitable for evaluating accent variability in French. To address this gap, we extend the CFPR dataset with explicit accent labels, providing a new benchmark for assessing the robustness of speech technology systems across diverse French accents. We additionally conduct a perceptual study with 87 human participants to evaluate the reliability and interpretability of these labels. Using this resource, we evaluated an eight-class French accent classifier trained on Common Voice data. The first results highlight both the complexity of automatic French accent recognition in low-resource settings, and the difficulty for French-speakers to perceive all the linguistic variabilities in French-speaking countries.</abstract>
<identifier type="citekey">fabre-etal-2026-building</identifier>
<identifier type="doi">10.63317/5ayaxbnxjfen</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.450/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5711</start>
<end>5721</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Dataset for French Accent Classification Evaluation: Are We There Yet?
%A Fabre, Diandra
%A Avanzi, Mathieu
%A Portet, François
%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 fabre-etal-2026-building
%X Current evaluation practices in speech processing systems often overlook the diversity of spoken accents, leading to significant performance disparities across speaker groups. This issue largely comes from biases and imbalances in training corpora, and is further compounded by the scarcity of open-source datasets suitable for evaluating accent variability in French. To address this gap, we extend the CFPR dataset with explicit accent labels, providing a new benchmark for assessing the robustness of speech technology systems across diverse French accents. We additionally conduct a perceptual study with 87 human participants to evaluate the reliability and interpretability of these labels. Using this resource, we evaluated an eight-class French accent classifier trained on Common Voice data. The first results highlight both the complexity of automatic French accent recognition in low-resource settings, and the difficulty for French-speakers to perceive all the linguistic variabilities in French-speaking countries.
%R 10.63317/5ayaxbnxjfen
%U https://aclanthology.org/2026.lrec-1.450/
%U https://doi.org/10.63317/5ayaxbnxjfen
%P 5711-5721
Markdown (Informal)
[Building a Dataset for French Accent Classification Evaluation: Are We There Yet?](https://aclanthology.org/2026.lrec-1.450/) (Fabre et al., LREC 2026)
ACL