Tröger, J., Dörr, F., Schwed, L., Linz, N., König, A., Thies, T., Orozco-Arroyave, J., and Rusz, J. (2024). An Automatic Measure for Speech Intelligibility in Dysarthrias – Validation across Multiple Languages and Neurological Disorders. Frontiers in Digital Health, 6: 1440986. doi:10.3389/fdgth.2024.1440986
Abstract
Dysarthria, a motor speech disorder caused by muscle weakness or paralysis, severely impacts speech intelligibility and quality of life. The condition is prevalent in motor speech disorders such as Parkinson’s Disease (PD), atypical parkinsonism such as progressive supranuclear palsy (PSP), Huntington’s Disease (HD) or amyotrophic lateral sclerosis (ALS). Improving intelligibility is not only an outcome that matters to patients but can also play a critical role as an endpoint in clinical research and drug development.This study validates a digital measure for speech intelligibility, the ki: SB-M intelligibility score, across various motor speech disorders and languages following the Digital Medicine Society (DiMe) V3 framework.The study utilized four datasets including healthy controls (HC) as well as patients with PD, HD, PSP and ALS from Czech, Colombian, and German populations. Participants’ speech intelligibility was assessed using the ki: SB-M intelligibility score which is derived from automatic speech recognition (ASR) systems. Verification with inter-ASR reliability and temporal consistency, analytical validation with correlations to gold standard clinical dysarthria scores in each disease, and clinical validation with group comparisons between HC and patients were performed.Verification showed good to excellent inter-rater reliability between ASR systems as well as fair to good consistency. Analytical validation revealed significant correlations between the SB-M intelligibility score and established clinical measures for speech impairments across all patient groups and languages. Clinical validation demonstrated significant differences in intelligibility scores between pathological groups and healthy controls, indicating the measure’s discriminative capability. The ki: SB-M intelligibility score is a reliable, valid, and clinically relevant tool for assessing speech intelligibility in motor speech disorders. It holds promise for enhancing clinical trials through automated, objective, and scalable assessments. Future studies should explore its utility in monitoring disease progression and therapeutic efficacy as well as adding data from further dysarthrias to the validation.