Automatic estimation of verbal fluency index in people with Motor Neuron Disease using ASR alignment and pause modelling

2026-09-22

AI Summary

This study addresses the challenge of assessing the Verbal Fluency Index (VFI) in patients with motor neuron disease (MND) whose speech is impaired by dysarthria. We propose an automated evaluation framework that integrates automatic speech recognition with pause modeling. By combining WhisperX and Silero VAD technologies, the method optimizes timestamp alignment and extracts fine-grained pause features, overcoming the limitations of conventional acoustic features to enable the automatic quantification and regression prediction of clinically interpretable metrics. Experimental results demonstrate that the proposed model significantly outperforms baseline methods, achieving R² values of 0.9 and 0.8 for predicting P-words and N-words, respectively. These findings validate the robustness and clinical feasibility of the framework in speech-impaired scenarios.

Abstract

Monitoring cognitive impairment (CI) in motor neuron disease (MND) is essential for timely treatment and care, yet challenging due to co-occurring speech difficulties. The Edinburgh Cognitive and Behavioural ALS Screen (ECAS) provides a robust metric for CI assessment, with the Verbal Fluency Index (VFI) a central element. Building on recent advances in automated speech analysis, this study proposes a system for estimating VFI. It leverages a unique MND dataset and combines ASR (WhisperX) and VAD (Silero) with refined timestamping to predict the VFI and extract several clinically interpretable measures. Our approach outperformed systems based on traditional acoustic features and self-supervised embeddings, evaluated using multiple regression algorithms. Clinically inspired features consistently outperformed the other sets, with the best models achieving strong results (P-words: R2 0.9, NRMSE 0.05; S-words: R2 0.8, NRMSE 0.08), demonstrating the feasibility of automated VFI estimation.

Problem

• Motor Neuron Disease
• Cognitive Impairment
• Verbal Fluency Index
• Automated Speech Analysis
• ECAS

Innovation

• Verbal Fluency Index
• Motor Neuron Disease
• ASR alignment
• Pause modelling
• Clinically interpretable features