%Aigaion2 BibTeX export from Idiap Publications %Saturday 23 November 2024 09:20:07 AM @INPROCEEDINGS{Janbakhshi_ICASSP_2021, author = {Janbakhshi, Parvaneh and Kodrasi, Ina and Bourlard, Herv{\'{e}}}, projects = {Idiap, MOSPEEDI}, month = may, title = {AUTOMATIC DYSARTHRIC SPEECH DETECTION EXPLOITING PAIRWISE DISTANCE-BASED CONVOLUTIONAL NEURAL NETWORKS}, booktitle = {45th International Conference on Acoustics, Speech, and Signal Processing}, year = {2021}, pages = {7328–7332}, location = {Toronto, Canada}, crossref = {Janbakhshi_Idiap-RR-32-2020}, pdf = {https://publications.idiap.ch/attachments/papers/2021/Janbakhshi_ICASSP_2021.pdf} } crossreferenced publications: @TECHREPORT{Janbakhshi_Idiap-RR-32-2020, author = {Janbakhshi, Parvaneh and Kodrasi, Ina and Bourlard, Herv{\'{e}}}, projects = {Idiap, MOSPEEDI}, month = {12}, title = {AUTOMATIC DYSARTHRIC SPEECH DETECTION EXPLOITING PAIRWISE DISTANCE-BASED CONVOLUTIONAL NEURAL NETWORKS}, type = {Idiap-RR}, number = {Idiap-RR-32-2020}, year = {2020}, institution = {Idiap}, note = {Submitted}, 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.}, pdf = {https://publications.idiap.ch/attachments/reports/2020/Janbakhshi_Idiap-RR-32-2020.pdf} }