@inproceedings{alshehri-etal-2026-parameter,
    title = "Parameter-Efficient Adaptation of Self-Supervised Models for {A}rabic Speech Recognition",
    author = "Alshehri, Wafa Mohammed  and
      Al-khatib, Wasfi G.  and
      Amro, Mohammad Ismail",
    booktitle = "Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.abjadnlp-1.40/",
    pages = "322--328",
    abstract = "Arabic speech recognition systems face distinct challenges due to the language{'}s complex morphology and dialectal variations. Self-supervised models (SSL) like XLS-R have shown promising results, but their size with over than 300 million of parameters, makes fine-tuning computationally expensive. In this work, we present the first comparative study of parameter-efficient fine-tuning (PEFT), specifically LoRA and DoRA, applied to XLS-R for Arabic ASR. We evaluate on the newly released Common Voice Arabic V24.0 dataset, establishing new benchmarks. Our full fine-tuning achieves state-of-the-art results among XLS-R-based models with 23.03{\%} Word Error Rate (WER). In our experiments, LoRA achieved a 36.10{\%} word error rate (WER) while training just 2{\%} of the model{'}s parameters. DoRA reached 45.20{\%} WER in initial experiments. We analyze the trade-offs between accuracy and efficiency, offering practical guidance for developing Arabic ASR systems when computational resources are limited. The models and code are publicly available."
}