{"ID":5443773,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-03T13:50:35.156039308Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31722","arxiv_id":"2606.31722","title":"Adapting Foundation ASR Models to Dysarthric Speech: A Case Study","abstract":"Automatic speech recognition (ASR) systems often perform poorly in dysarthric speech, limiting their usefulness to affected speakers in everyday communication. This paper presents a personalized ASR system for a dysarthric speaker, built by adapting a foundation ASR model to speaker-specific data. Using the TEQST tool, we collected 92 hours of read speech and later added 8.8 hours of user corrections gathered through a deployed mobile application. Starting from Whisper, fine-tuning reduced word error rate to 15.8% with only 1.4 hours of adaptation data, reached 10.7% with 22.5 hours, and achieved the best result of 9.7% when using all available data including the corrections. Using LoRA adaptation and/or Qwen3-ASR as foundation model performed worse in this setting. The results show that personalized fine-tuning can make foundation ASR models substantially more effective for dysarthric speech and suitable for practical deployment.","short_abstract":"Automatic speech recognition (ASR) systems often perform poorly in dysarthric speech, limiting their usefulness to affected speakers in everyday communication. This paper presents a personalized ASR system for a dysarthric speaker, built by adapting a foundation ASR model to speaker-specific data. Using the TEQST tool,...","url_abs":"https://arxiv.org/abs/2606.31722","url_pdf":"https://arxiv.org/pdf/2606.31722v1","authors":"[\"Christian Huber\",\"Laura Kernahan\",\"Alexander Waibel\"]","published":"2026-06-30T14:23:49Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"LoRA\"]","has_code":false}