abstract: Often termed the "gold standard" in the differential diagnosis of dysarthria, the etiology-based Mayo Clinic classification approach has been used nearly exclusively by clinicians since the early 1970s. However, the current descriptive method results in a distinct overlap of perceptual features across various etiologies, thus limiting the clinical utility of such a system for differential diagnosis. Acoustic analysis may provide a more objective measure for improvement in overall reliability (Guerra & Lovely, 2003) of classification. The following paper investigates the potential use of a taxonomical approach to dysarthria. The purpose of this study was to identify a set of acoustic correlates of perceptual dimensions used to group similarly sounding speakers with dysarthria, irrespective of disease etiology. The present study utilized a free classification auditory perceptual task in order to identify a set of salient speech characteristics displayed by speakers with varying dysarthria types and perceived by listeners, which was then analyzed using multidimensional scaling (MDS), correlation analysis, and cluster analysis. In addition, discriminant function analysis (DFA) was conducted to establish the feasibility of using the dimensions underlying perceptual similarity in dysarthria to classify speakers into both listener-derived clusters and etiology-based categories. The following hypothesis was identified: Because of the presumed predictive link between the acoustic correlates and listener-derived clusters, the DFA classification results should resemble the perceptual clusters more closely than the etiology-based (Mayo System) classifications. Results of the present investigation's MDS revealed three dimensions, which were significantly correlated with 1) metrics capturing rate and rhythm, 2) intelligibility, and 3) all of the long-term average spectrum metrics in the 8000 Hz band, which has been linked to degree of phonemic distinctiveness (Utianski et al., February 2012). A qualitative examination of listener notes supported the MDS and correlation results, with listeners overwhelmingly making reference to speaking rate/rhythm, intelligibility, and articulatory precision while participating in the free classification task. Additionally, acoustic correlates revealed by the MDS and subjected to DFA indeed predicted listener group classification. These results beget acoustic measurement as representative of listener perception, and represent the first phase in supporting the use of a perceptually relevant taxonomy of dysarthria. / Dissertation/Thesis / M.S. Communication Disorders 2012

L’intelligibilité de la parole est un véritable enjeu dans la prise en charge des personnes présentant un trouble de la production de la parole pathologique (TPPP). L’usage de ce terme, avec un sens commun recouvrant le domaine de la compréhension, et un sens restreint répondant à la mesure du transfert d’information linguistique dans un contexte de test, entretient une ambigüité ; ambigüité qui entrave le développement des concepts de prise en charge. L’objectif de ce travail de thèse est, à travers trois groupes d’expériences autour de la notion d’intelligibilité, de proposer un cadre conceptuel pouvant servir à organiser la prise en charge des TPPP et à identifier les questions de recherche fondamentale impliquées dans la problématique de l’intelligibilité dans les TPPP.L’objectif principal du premier groupe d’expériences est d’étudier la place de l’intelligibilité dans les stratégies cognitives sous-jacentes à la perception de la parole pathologique. La méthode utilisée est une catégorisation libre..La deuxième série d’expériences est consacrée à la manière dont un groupe d’experts réalise une tâche de jugement de sévérité comparée à une tâche de jugement d’intelligibilité. Le troisième groupe d’expériences cherche à déterminer les cibles les plus efficaces dans la prise en charge des TPPP. Elle repose sur l’hypothèse suivante : la conservation d’une perception juste d’un phonème ou d’une syllabe malgré sa distorsion pathologique permet de déterminer sa contribution à l’intelligibilité et participe à la définition de la notion de robustesse perceptive. Pour tester cette hypothèse, une méthode d’analyse du taux de perception obtenu par un jury d’auditeurs, en fonction du degré de vraisemblance issu d’un système automatique de reconnaissance a été formalisée. Les résultats de ces expériences, interprétées sous l’éclairage croisé des théories sur la perception et de la production de la parole et des modèles de santé, nous ont permis de proposer une définition des différents concepts dans la perspective de la classification internationale du fonctionnement. / The intelligibility of speech is a real challenge for the management of speech disorders. The use of this word, with a common meaning of comprehension and, a specific meaning in a context of test, of measurement of the information transfer, carries some ambiguity, which could hinder the concept of management.The purpose of this work is to propose a conceptual framework for the management of pathological speech production (PSP) through three kinds of experiments. The aim of the first set of experiments is to study the place of the intelligibility within the underlying cognitive strategies of the perception of pathological speech.A free classification method is used with a corpus of sentences read by 33 speakers: 20 patients with speech disorders (a pathological speech production due to neurological diseases or sequellae of cancer or malformative lesions) and 13 normal subjects. The second set of experiments studies the way an expert group performs evaluation of severity compared to evaluation of intelligibility. During an off line experiment, the corpus of the previous study filled by a corpus of different sentences by speaker, was presented to 5 judges (logopedists and phoniatriciansThe third group of experiments looks for the most efficient targets for managing speech disorders. It‘s based on the following assumption: the preservation of a correct perception of a phoneme or a syllable, despite its pathological distortion, allows to determine its contribution to intelligibility and participates to the notion of perceptive robustness. For testing this assumption, was proposed a method of analysis by the identification score (obtained by a jury of listeners) function of the degree of” plausibility (obtained by an automatic system for speech recognition). The outcome of these experiments, adopting the points of view of some perception theories of SD mixed with health models allow us to precise the definition of the main concepts in the prospect of the international classification of functioning.