Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.15516 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915811666427904 |
|---|---|
| author | Agarwal, Dhruuv Zhang, Harry Yu, Yang Wang, Quan |
| author_facet | Agarwal, Dhruuv Zhang, Harry Yu, Yang Wang, Quan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15516 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Universal Personalizer: Few-Shot Dysarthric Speech Recognition via Meta-Learning Agarwal, Dhruuv Zhang, Harry Yu, Yang Wang, Quan Audio and Speech Processing Sound 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. |
| title | The Universal Personalizer: Few-Shot Dysarthric Speech Recognition via Meta-Learning |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2509.15516 |