Automatic dysarthric speech detection exploiting pairwise distance-based convolutional neural networks

TL;DR

This paper introduces a novel CNN-based method for dysarthric speech detection that analyzes pairwise distance matrices of articulatory features, achieving high accuracy across multiple languages and pathologies.

Contribution

It proposes a new approach using pairwise distance matrices and CNNs for dysarthric speech detection, optimized end-to-end, outperforming existing CNN baselines.

Findings

High detection accuracy on multiple language databases

Outperforms other CNN-based methods

Effective across different speech pathologies

Abstract

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.