CONF Janbakhshi_ICASSP_2021/IDIAP AUTOMATIC DYSARTHRIC SPEECH DETECTION EXPLOITING PAIRWISE DISTANCE-BASED CONVOLUTIONAL NEURAL NETWORKS Janbakhshi, Parvaneh Kodrasi, Ina Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/papers/2021/Janbakhshi_ICASSP_2021.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Janbakhshi_Idiap-RR-32-2020 Related documents 45th International Conference on Acoustics, Speech, and Signal Processing Toronto, Canada 2021 7328–7332 REPORT Janbakhshi_Idiap-RR-32-2020/IDIAP AUTOMATIC DYSARTHRIC SPEECH DETECTION EXPLOITING PAIRWISE DISTANCE-BASED CONVOLUTIONAL NEURAL NETWORKS Janbakhshi, Parvaneh Kodrasi, Ina Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2020/Janbakhshi_Idiap-RR-32-2020.pdf PUBLIC Idiap-RR-32-2020 2020 Idiap December 2020 Submitted 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.