Speaker-independent dysarthria severity classification using self-supervised transformers and multi-task learning
File(s)
Published version
Author(s)
Kadirvelu, Balasundaram
Stumpf, Lauren
Waibel, Sigourney
Faisal, A Aldo
Type
Journal Article
Abstract
Dysarthria, characterised by slurred speech, is a hallmark of many neurological disorders and brain trauma. Clinical assessment requires an audio-visual investigation by a trained healthcare expert, who evaluates criteria such as respiration, phonation, articulation, resonance, and prosody during speech. Quantitative assessment of dysarthria is challenging due to its complexity, variability, and the subjective nature of human-observation-based scoring methods. We present a novel machine-learning framework using transformers for stratifying and monitoring patient speech. Our framework integrates a wav2vec 2.0 model, pre-trained on raw speech data from healthy individuals. To reduce reliance on speaker-specific characteristics and effectively manage the intrinsic intra-class variability of dysarthric speech, we employ a contrastive learning strategy with a multi-task objective: cross-entropy loss for classifying dysarthria severity, and triplet margin loss to ensure latent embeddings are grouped by severity rather than by speaker. This Speaker-Agnostic Latent Regularisation (SALR) framework provides an objective, accessible, and cost-effective alternative to traditional assessments. On the UA-Speech dataset, SALR achieved 70.5% accuracy and 59.2% F1 using leave-one-subject-out cross-validation—a 16.5% absolute (30% relative) improvement over prior benchmarks. Explainability analysis indicates that our multi-task objective enhances the ordinal structure of the latent space, reducing dependence on speaker-specific cues and demonstrating robustness and generalisability. In conclusion, this proof-of-concept study demonstrates the potential of the SALR framework for speaker-independent dysarthria severity classification, with potential implications for broader clinical applications in automated dysarthria assessments.
Editor(s)
Al-Jumeily OBE, Dhiya
Date Issued
2025-11-12
Date Acceptance
2025-10-18
Citation
PLOS Digital Health, 2025, 4 (11)
ISSN
2767-3170
Publisher
Public Library of Science (PLoS)
Journal / Book Title
PLOS Digital Health
Volume
4
Issue
11
Copyright Statement
© 2025 Kadirvelu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/41223239
PII: PDIG-D-24-00243
Subjects
Health Care Sciences & Services
Life Sciences & Biomedicine
Medical Informatics
MODELS
Science & Technology
SPEECH
Publication Status
Published
Coverage Spatial
United States
Article Number
e0001076
Date Publish Online
2025-11-12