Speech Recognition-based Feature Extraction for Enhanced Automatic Severity Classification in Dysarthric Speech
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913599111299072 |
|---|---|
| author | Choi, Yerin Lee, Jeehyun Koo, Myoung-Wan |
| author_facet | Choi, Yerin Lee, Jeehyun Koo, Myoung-Wan |
| contents | Due to the subjective nature of current clinical evaluation, the need for automatic severity evaluation in dysarthric speech has emerged. DNN models outperform ML models but lack user-friendly explainability. ML models offer explainable results at a feature level, but their performance is comparatively lower. Current ML models extract various features from raw waveforms to predict severity. However, existing methods do not encompass all dysarthric features used in clinical evaluation. To address this gap, we propose a feature extraction method that minimizes information loss. We introduce an ASR transcription as a novel feature extraction source. We finetune the ASR model for dysarthric speech, then use this model to transcribe dysarthric speech and extract word segment boundary information. It enables capturing finer pronunciation and broader prosodic features. These features demonstrated an improved severity prediction performance to existing features: balanced accuracy of 83.72%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03784 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Speech Recognition-based Feature Extraction for Enhanced Automatic Severity Classification in Dysarthric Speech Choi, Yerin Lee, Jeehyun Koo, Myoung-Wan Sound Artificial Intelligence Audio and Speech Processing Due to the subjective nature of current clinical evaluation, the need for automatic severity evaluation in dysarthric speech has emerged. DNN models outperform ML models but lack user-friendly explainability. ML models offer explainable results at a feature level, but their performance is comparatively lower. Current ML models extract various features from raw waveforms to predict severity. However, existing methods do not encompass all dysarthric features used in clinical evaluation. To address this gap, we propose a feature extraction method that minimizes information loss. We introduce an ASR transcription as a novel feature extraction source. We finetune the ASR model for dysarthric speech, then use this model to transcribe dysarthric speech and extract word segment boundary information. It enables capturing finer pronunciation and broader prosodic features. These features demonstrated an improved severity prediction performance to existing features: balanced accuracy of 83.72%. |
| title | Speech Recognition-based Feature Extraction for Enhanced Automatic Severity Classification in Dysarthric Speech |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2412.03784 |