@inproceedings{danilevskyi-etal-2026-addressing,
    title = "Addressing Accent Disparities in Automatic Speech Recognition: A Comparative Study of Single and Two-Step Adaptation",
    author = "Danilevskyi, Mykhailo  and
      Perez-Tellez, Fernando  and
      Vasic, Jelena",
    editor = "Hosseini-Kivanani, Nina  and
      Brutti, Alessio  and
      Matassoni, Marco  and
      Dowerah, Sandipana  and
      Liga, Davide  and
      Schommer, Christoph",
    booktitle = "Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis ({SPEAKABLE}) @ {LREC} 2026",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/backfill-openreview/2026.speakable-1.9/",
    doi = "10.63317/3zjiz9fsk4fy",
    pages = "79--85",
    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."
}