Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912545964556288 |
|---|---|
| author | Mujtaba, Dena Mahapatra, Nihar |
| author_facet | Mujtaba, Dena Mahapatra, Nihar |
| contents | Stuttering -- characterized by involuntary disfluencies such as blocks, prolongations, and repetitions -- is often misinterpreted by automatic speech recognition (ASR) systems, resulting in elevated word error rates and making voice-driven technologies inaccessible to people who stutter. The variability of disfluencies across speakers and contexts further complicates ASR training, compounded by limited annotated stuttered speech data. In this paper, we investigate fine-tuning ASRs for stuttered speech, comparing generalized models (trained across multiple speakers) to personalized models tailored to individual speech characteristics. Using a diverse range of voice-AI scenarios, including virtual assistants and video interviews, we evaluate how personalization affects transcription accuracy. Our findings show that personalized ASRs significantly reduce word error rates, especially in spontaneous speech, highlighting the potential of tailored models for more inclusive voice technologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00853 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches Mujtaba, Dena Mahapatra, Nihar Sound Audio and Speech Processing Stuttering -- characterized by involuntary disfluencies such as blocks, prolongations, and repetitions -- is often misinterpreted by automatic speech recognition (ASR) systems, resulting in elevated word error rates and making voice-driven technologies inaccessible to people who stutter. The variability of disfluencies across speakers and contexts further complicates ASR training, compounded by limited annotated stuttered speech data. In this paper, we investigate fine-tuning ASRs for stuttered speech, comparing generalized models (trained across multiple speakers) to personalized models tailored to individual speech characteristics. Using a diverse range of voice-AI scenarios, including virtual assistants and video interviews, we evaluate how personalization affects transcription accuracy. Our findings show that personalized ASRs significantly reduce word error rates, especially in spontaneous speech, highlighting the potential of tailored models for more inclusive voice technologies. |
| title | Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.00853 |