1517 articles – 1652 notices  [english version]
HAL : hal-00530199, version 1

Fiche détaillée  Récupérer au format
2nd International Symposium Basal Ganglia Speech Disorders & Deep Brain Stimulation, Aix en Provence : France (2010)
A new approach for an acoustic- phonetic description of dysarthria
Lise Crevier-Buchman ( ) 1, 2, Cécile Fougeron 1, Corinne Fredouille 3, Alain Ghio 4, Christine Meunier 4, Céline Delooze 4, Danielle Duez 4, Cédric Gendrot 1, Thierry Legou 4, Nathalie Lévêque 1, Nicolas Audibert 3, 5, Antonia Colazo-Simon 1, Claire Pillot-Loiseau 1, Serge Pinto 4, Gilles Pouchoulin 3, Danièle Robert 4, François Viallet 4, Coralie Vincent 1, Bernard Teston 4, Claude Chevrie-Muller 6
(29/06/2010)

A multidisciplinary team composed of phoneticians, clinicians, computer science engineers and automatic speech processing want to 1) identify and quantify reliable markers which are characteristic of different types of dysarthric speech profile, and could be followed in time (severity evaluation, disease progression, and treatment efficacy) ; 2) select reliable and robust French acoustic phonetic criteria able to distinguish normal and dysarthric speech, and different dysarthria types. The acoustic evaluation based on semi-automatic extraction of selected acoustic parameters (patients vs controls) is compared with : 1) perceptual evaluation of selected speech dimensions 2) expert annotation of the impaired part of speech by 10 expert judges for 30 patients with ALS dysarthria, 30 patients with ataxic dysarthria and 30 patients with Parkinsonian one. Assumption that an acoustico-phonetic description of dysarthric speech has to be apprehended in a comprehensive fashion according to the multiple dimensions of speech production that can be impaired, but also by a systematic testing of all potentially informative acoustic criteria for every dysarthric speakers. Observing type and range of variations due to motor control deficit can help for a comprehensive model of speech variation for normal speakers. A better understanding of the variations that permit to consider a dysarthric speech as deviant could provide insights to the boundary between normal and pathological speech.
1 :  Laboratoire de Phonétique et Phonologie (LPP)
CNRS : UMR7018 – Université Paris III - Sorbonne nouvelle
2 :  Hôpital européen Georges Pompidou
Assistance publique - Hôpitaux de Paris (AP-HP) – Hôpital européen Georges Pompidou – Université Paris V - Paris Descartes
3 :  Laboratoire Informatique d'Avignon (LIA)
Université d'Avignon – Centre d'Enseignement et de Recherche en Informatique - CERI
4 :  Laboratoire Parole et Langage (LPL)
CNRS : UMR6057 – Université de Provence - Aix-Marseille I
5 :  Grenoble Images Parole Signal Automatique (GIPSA-lab)
CNRS : UMR5216 – Université Joseph Fourier - Grenoble I – Université Pierre-Mendès-France - Grenoble II – Université Stendhal - Grenoble III – Institut Polytechnique de Grenoble - Grenoble Institute of Technology
6 :  Modèles, Dynamiques, Corpus (MoDyCo)
CNRS : UMR7114 – Université Paris X - Paris Ouest Nanterre La Défense
Sciences de l'Homme et Société/Linguistique
Dysarthria – acoustic analysis – multidisciplinary team – semi-automatic extraction – normal speech – dysarthric speech