%Aigaion2 BibTeX export from Idiap Publications
%Friday 05 December 2025 09:52:09 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}
}