An artificial intelligence-based audio recognition system for dysarthria home-based rehabilitation: A proof-of-concept study
Ein KI-basiertes Audioerkennungssystem für die häusliche Rehabilitation bei Dysarthrie: Proof-of-Concept-Studie
PLOS Digital Health · 21.10.2026 · 5 (10) · e0001794
DOI: 10.1371/journal.pdig.0001794 ↗Auf einen Blick
Whisper-ST1 klassifizierte die Schwere der Dysarthrie in realen Audios mit 79 % per-speaker F1. Die Übereinstimmung mit zwei Logopäd:innen war hoch.
Fragestellung
Wie gut lässt sich die Dysarthrie-Schwere aus Audiodateien mit einem feinabgestimmten, vortrainierten Spracherkennungsmodell klassifizieren?
Methode
Proof-of-Concept-Studie zur Entwicklung und Evaluation von Whisper-ST1; Feinabstimmung eines vortrainierten automatischen Spracherkennungsmodells auf Audiodaten.
Ergebnisse
Im Test auf Realwelt-Samples erreichte Whisper-ST1 79 % [67 %–100 %] per-speaker F1. Die Übereinstimmung mit zwei Sprachtherapeut:innen lag bei 0,814 [0,400–1,000] und 0,878 [0,647–1,000].
Einschränkungen
Performance auf weniger kontrollierter, realer Sprache war zuvor unzureichend charakterisiert.
Schlussfolgerung der Autor:innen
Die Ergebnisse zeigen die Machbarkeit, vortrainierte Sprachmodelle zur Klassifikation der Dysarthrie-Schwere unter heterogenen Audiobedingungen zu nutzen.
Kernaussagen
- 79 % [67 %–100 %] per-speaker F1 in Realwelt-Samples
- Hohe Übereinstimmung mit zwei Sprachtherapeut:innen
- Fehler meist nur zwischen benachbarten Schweregraden
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 21.10.2026. Verfasst von Vicente Sancenon und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Future Technology & Innovation - Data, AI & Innovation, Synapxe, Singapore, Singapore. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Dysarthria is a common motor speech disorder affecting individuals with neurological conditions, with high prevalence among stroke survivors. Effective treatment of dysarthria requires accurate assessment of severity and the provision of speech exercises tailored to the degree of impairment. However, traditional speech intervention faces several limitations, including limited accessibility to therapists and low treatment adherence rates. AI-driven solutions have the potential to address these limitations by automating the detection of dysarthria severity and recommending personalized exercises. Although substantial progress has been made in the automated detection and classification of dysarthria severity, the performance of these approaches on less controlled, real-world speech remains insufficiently characterized. This proof-of-concept study describes the development and evaluation of Whisper-ST1, a novel framework for classifying dysarthric speech severity from audio files by fine-tuning a pretrained automatic speech recognition model. Our framework builds on previous studies by incorporating real-world data alongside traditional research datasets, adapting a model architecture pretrained on a large corpus of audio data, applying a progressive unfreezing strategy to prevent catastrophic forgetting of relevant speech features while promoting flexible adaptation to the new task, and implementing an ordinal regression loss to minimize the impact of misclassification errors. Ablation experiments demonstrate the performance contributions of individual pipeline components in isolation. Whisper-ST1 achieves 79% [67% – 100%] per-speaker F1 in the classification of dysarthria severity when tested on real-world samples, and shows strong agreement with two speech therapists’ ratings of dysarthria (Weighted Cohen’s kappa of 0.814 [0.400 – 1.000] and 0.878 [0.647 – 1.000]), comparable to inter-therapist agreement (0.851 [0.550 – 1.000]). Model errors are predominantly confined to adjacent severity levels, suggesting preservation of ordinal structure. These findings demonstrate the feasibility of leveraging pretrained speech models for dysarthria severity classification in heterogeneous audio conditions. and provide a foundational step toward AI-assisted tools for remote monitoring and support of dysarthria rehabilitation.
Autor:innen und Institutionen
- Department of Future Technology & Innovation - Data, AI & Innovation, Synapxe, Singapore, Singapore.
- Rehabilitation, Ng Teng Fong General Hospital and Jurong Community Hospital, National University Health System, Singapore, Singapore.
- Department of Post-Acute & Continuing Care, Jurong Community Hospital, National University Health System, Singapore, Singapore.
- Division of Rehabilitation Medicine, Department of Medicine, National University Hospital, National University Health System, Singapore, Singapore.
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore.
- Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
ORCID-Profile: Vicente Sancenon, Elvina K W Tay
Zitieren
APA
Sancenon, V., Oh, P. Y. S., Tay, E. K. W., Lee, J. Z. X., Soon, M. L. E., Goh, H. L., Oey, N., & Ta, A. W. A. (2026). An artificial intelligence-based audio recognition system for dysarthria home-based rehabilitation: A proof-of-concept study. PLOS Digital Health, 5(10), e0001794. https://doi.org/10.1371/journal.pdig.0001794
Vancouver
Sancenon V, Oh PYS, Tay EKW, Lee JZX, Soon MLE, Goh HL, et al. An artificial intelligence-based audio recognition system for dysarthria home-based rehabilitation: A proof-of-concept study. PLOS Digital Health. 2026;5(10):e0001794. doi:10.1371/journal.pdig.0001794
BibTeX
@article{Sancenon2026,
author = {Sancenon, Vicente and Oh, Pamela Y S and Tay, Elvina K W and Lee, Jarrod Z X and Soon, Megan L E and Goh, Han Leong and Oey, Nicodemus and Ta, Andy W A},
title = {An artificial intelligence-based audio recognition system for dysarthria home-based rehabilitation: A proof-of-concept study},
journal = {PLOS Digital Health},
year = {2026},
volume = {5},
number = {10},
pages = {e0001794},
doi = {10.1371/journal.pdig.0001794}
}
EUVIMED