Détection automatique d’anomalies sur deux styles de parole dysarthrique: parole lue vs spontanée (Automatic anomaly detection for dysarthria across two speech styles : read vs spontaneous speech)[In French]

L'evaluation perceptive de la parole pathologique reste le standard dans la pratique clinique pour le diagnostic et le suivi des patients. De telles methodes incluent plusieurs tâches telles que la lecture, la parole spontanee, le chant, les mots isoles, la voyelle tenue, etc. Dans ce contexte, les outils de traitement automatique de la parole ont montre leur pertinence dans l'evaluation de la qualite de parole ainsi que dans le cadre de la communication amelioree et alternative (CAA) pour les patients atteints de troubles de parole. Cependant, peu de travaux ont etudie l'utilisation de ces outils sur la parole spontanee. Ce papier examine le comportement d'un systeme de detection automatique d'anomalies au niveau phoneme face a la parole dysarthrique lue et spontanee. Le comportement du systeme revele une variabilite inter-pathologique a travers les styles de parole.

[1]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[2]  Raymond D. Kent,et al.  Acoustic studies of dysarthric speech: methods, progress, and potential. , 1999, Journal of communication disorders.

[3]  R. Guiloff,et al.  Dysarthria in amyotrophic lateral sclerosis: A review , 2010, Amyotrophic lateral sclerosis : official publication of the World Federation of Neurology Research Group on Motor Neuron Diseases.

[4]  John J Sidtis,et al.  Dramatic effects of speech task on motor and linguistic planning in severely dysfluent parkinsonian speech , 2012, Clinical linguistics & phonetics.

[5]  Corinne Fredouille,et al.  Automatic Detection of Phone-Based Anomalies in Dysarthric Speech , 2015, ACM Trans. Access. Comput..

[6]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[7]  Guillaume Gravier,et al.  The ESTER phase II evaluation campaign for the rich transcription of French broadcast news , 2005, INTERSPEECH.

[8]  Daniel Kempler,et al.  Effect of Speech Task on Intelligibility in Dysarthria: A Case Study of Parkinson's Disease , 2002, Brain and Language.

[9]  C. Ludlow,et al.  Manual of Nerve Conduction Velocity and Clinical Neurophysiology, 3rd Ed. , 1994, Neurology.

[10]  Carmichael Jn,et al.  Introducing objective acoustic metrics for the frenchay dysarthria assessment procedure. , 2007 .

[11]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[12]  Gary L. Pattee,et al.  Bulbar and speech motor assessment in ALS: Challenges and future directions , 2013, Amyotrophic lateral sclerosis & frontotemporal degeneration.

[13]  G. Docherty,et al.  Phonetic variation in dysarthric speech as a function of sampling task. , 1995, European journal of disorders of communication : the journal of the College of Speech and Language Therapists, London.

[14]  Jean-Pierre Martens,et al.  Automated Intelligibility Assessment of Pathological Speech Using Phonological Features , 2009, EURASIP J. Adv. Signal Process..

[15]  Myung Jong Kim,et al.  Automatic Assessment of Dysarthric Speech Intelligibility Based on Selected Phonetic Quality Features , 2012, ICCHP.

[16]  Corinne Fredouille,et al.  Automatic Detection of Abnormal Zones in Pathological Speech , 2011, ICPhS.

[17]  Corinne Fredouille,et al.  Automatic speech processing for dysarthria: A study of inter-pathology variability , 2015, ICPhS.

[18]  P. Green,et al.  Automatic speech recognition and training for severely dysarthric users of assistive technology: The STARDUST project , 2006, Clinical linguistics & phonetics.

[19]  A. Aronson,et al.  Differential diagnostic patterns of dysarthria. , 1969, Journal of speech and hearing research.

[20]  Heidi Christensen,et al.  homeService: Voice-enabled assistive technology in the home using cloud-based automatic speech recognition , 2013, SLPAT.

[21]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.