Automatic Dysarthric Speech Detection Exploiting Pairwise Distance-Based Convolutional Neural Networks

• Main Authors: Janbakhshi, Parvaneh, Kodrasi, Ina, Bourlard, Herve
• Format: Conference Proceeding
• Language: English
• Subjects: Amyotrophic Lateral Sclerosis; convolutional neural network; Dysarthria; Feature extraction; Neural networks; pairwise distance; Parkinson's disease; Pathology; Signal processing; Voice activity detection
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP39728.2021.9413922

Automatic dysarthric speech detection can provide reliable and cost-effective computer-aided tools to assist the clinical diagnosis and management of dysarthria. In this paper we propose a novel automatic dysarthric speech detection approach based on analyses of pairwise distance matrices using convolutional neural networks (CNNs). We represent utterances through articulatory posteriors and consider pairs of phonetically-balanced representations, with one representation from a healthy speaker (i.e., the reference representation) and the other representation from the test speaker (i.e., test representation). Given such pairs of reference and test representations, features are first extracted using a feature extraction front-end, a frame-level distance matrix is computed, and the obtained distance matrix is considered as an image by a CNN-based binary classifier. The feature extraction, distance matrix computation, and CNN-based classifier are jointly optimized in an end-to-end framework. Experimental results on two databases of healthy and dysarthric speakers for different languages and pathologies show that the proposed approach yields a high dysarthric speech detection performance, outperforming other CNN-based baseline approaches.