{"ID":2868541,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.15516","arxiv_id":"2509.15516","title":"The Universal Personalizer: Few-Shot Dysarthric Speech Recognition via Meta-Learning","abstract":"Personalizing dysarthric ASR is hindered by demanding enrollment collection and per-user training. We propose a hybrid meta-training method for a single model, enabling zero-shot and few-shot on-the-fly personalization via in-context learning (ICL). On Euphonia, it achieves 13.9% Word Error Rate (WER), surpassing speaker-independent baselines (17.5%). On SAP Test-1, our 5.3% WER outperforms the challenge-winning team (5.97%). On Test-2, our 9.49% trails only the winner (8.11%) but without relying on techniques like offline model-merging or custom audio chunking. Curation yields a 40% WER reduction using random same-speaker examples, validating active personalization. While static text curation fails to beat this baseline, oracle similarity reveals substantial headroom, highlighting dynamic acoustic retrieval as the next frontier. Data ablations confirm rapid low-resource speaker adaptation, establishing the model as a practical personalized solution.","short_abstract":"Personalizing dysarthric ASR is hindered by demanding enrollment collection and per-user training. We propose a hybrid meta-training method for a single model, enabling zero-shot and few-shot on-the-fly personalization via in-context learning (ICL). On Euphonia, it achieves 13.9% Word Error Rate (WER), surpassing speak...","url_abs":"https://arxiv.org/abs/2509.15516","url_pdf":"https://arxiv.org/pdf/2509.15516v2","authors":"[\"Dhruuv Agarwal\",\"Harry Zhang\",\"Yang Yu\",\"Quan Wang\"]","published":"2025-09-19T01:40:57Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[\"Large Language Model\"]","has_code":false}