@inproceedings{elghazaly-etal-2025-fairness,
    title = "Fairness in Automatic Speech Recognition Isn{'}t a One-Size-Fits-All",
    author = "ElGhazaly, Hend  and
      Mirheidari, Bahman  and
      Christensen, Heidi  and
      Moosavi, Nafise Sadat",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1044/",
    doi = "10.18653/v1/2025.findings-emnlp.1044",
    pages = "19169--19178",
    ISBN = "979-8-89176-335-7",
    abstract = "Modern Automatic Speech Recognition (ASR) systems are increasingly deployed in high-stakes settings, including clinical interviews, public services, and educational tools, where equitable performance across speaker groups is essential. While pre-trained speech models like Whisper achieve strong overall accuracy, they often exhibit inconsistent group-level performance that varies across domains. These disparities are not fixed properties of the model, but emerge from the interaction between model, data, and task{---}posing challenges for fairness interventions designed in-domain.We frame fairness in ASR as a generalisation problem. We fine-tune a Whisper model on the Fair-Speech corpus using four strategies: basic fine-tuning, demographic rebalancing, gender-swapped data augmentation, and a novel contrastive learning objective that encourages gender-invariant representations. We evaluate performance across multiple aspects of fairness and utility, both in-domain and on three out-of-domain test sets: LibriSpeech, EdAcc, and CognoSpeak.Our findings show that the method with the best in-domain fairness performed worst out-of-domain, illustrating that fairness gains do not always generalise. Demographic balancing generalises more consistently, while our contrastive method offers a practical alternative: it achieves stable, cross-domain fairness improvements without requiring changes to the training data distribution, and with minimal accuracy trade-offs."
}