@article{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",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.450/",
    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."
}