Application of the Lognormal Model to the Vocal Tract Movement to Detect Neurological Diseases in Voice

In this paper a novel method to evaluate the quality of the voice signal is presented. Our novel hypothesis is that the first and second formants allow the estimation of the jaw-tongue dynamics. Once the velocity is computed, it is approximated by the Sigma-Lognormal model whose parameters enable to distinguish between normal and pathological voices. Three types of pathologies are used to test the method: Laryngeal Diseases, Parkinson and Amyotrophic Lateral Sclerosis. Preliminary results show that the novel features proposed are able to distinguish between parameters of normal and pathological voice. Moreover, it is also possible to discriminate between the three types of pathologies studied in this work.

[1]  Kun Xia,et al.  A new strategy of formant tracking based on dynamic programming , 2000, INTERSPEECH.

[2]  Laura J. Ball,et al.  Timing of speech deterioration in people with amyotrophic lateral sclerosis , 2002 .

[3]  Miguel Angel Ferrer-Ballester,et al.  Kinematic Modelling of Dipthong Articulation , 2016, Recent Advances in Nonlinear Speech Processing.

[4]  María Victoria Rodellar Biarge,et al.  Monitoring amyotrophic lateral sclerosis by biomechanical modeling of speech production , 2015, Neurocomputing.

[5]  Claudia Manfredi,et al.  Automatic identification of dysprosody in idiopathic Parkinson's disease , 2015, Biomed. Signal Process. Control..

[6]  Paavo Alku,et al.  Glottal wave analysis with Pitch Synchronous Iterative Adaptive Inverse Filtering , 1991, Speech Commun..

[7]  Christian O'Reilly,et al.  Design of a neuromuscular disorders diagnostic system using human movement analysis , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[8]  G. E. Peterson,et al.  Control Methods Used in a Study of the Vowels , 1951 .

[9]  Réjean Plamondon,et al.  Time-dependence between upper arm muscles activity during rapid movements: observation of the proportional effects predicted by the kinematic theory. , 2013, Human movement science.

[10]  Raymond D. Kent,et al.  Formant trajectory characteristics of males with amyotrophic lateral sclerosis. , 1992, The Journal of the Acoustical Society of America.

[11]  Julian Fiérrez,et al.  Variations of handwritten signatures with time: A sigma-lognormal analysis , 2013, 2013 International Conference on Biometrics (ICB).

[12]  F. Itakura.  Line spectrum representation of linear predictor coefficients of speech signals , 1975 .

[13]  M. Lindstrom,et al.  Articulatory movements during vowels in speakers with dysarthria and healthy controls. , 2008, Journal of speech, language, and hearing research : JSLHR.

[14]  Roman Cmejla,et al.  Acoustic investigation of stress patterns in Parkinson's disease. , 2014, Journal of voice : official journal of the Voice Foundation.

[15]  Réjean Plamondon,et al.  Strokes against stroke - strokes for strides , 2014, Pattern Recognit..

[16]  L. Ramig,et al.  Speech treatment for Parkinson’s disease , 2008, Expert review of neurotherapeutics.

[17]  Roman Cmejla,et al.  Acoustic assessment of voice and speech disorders in Parkinson's disease through quick vocal test , 2011, Movement disorders : official journal of the Movement Disorder Society.

[18]  R. Plamondon,et al.  A multi-level representation paradigm for handwriting stroke generation. , 2006, Human movement science.

[19]  S. Skodda,et al.  Speech rate and rhythm in Parkinson's disease , 2008, Movement disorders : official journal of the Movement Disorder Society.

[20]  Miguel Angel Ferrer-Ballester,et al.  Automatic Detection of Pathologies in The Voice by HOS Based Parameters , 2001, EURASIP J. Adv. Signal Process..

[21]  Réjean Plamondon,et al.  A kinematic theory of rapid human movements , 1995, Biological Cybernetics.

[22]  Christian O'Reilly,et al.  The lognormal handwriter: learning, performing, and declining , 2013, Front. Psychol..

[23]  Réjean Plamondon,et al.  Development of a Sigma-Lognormal representation for on-line signatures , 2009, Pattern Recognit..

[24]  Miguel Angel Ferrer-Ballester,et al.  Characterization of Healthy and Pathological Voice Through Measures Based on Nonlinear Dynamics , 2009, IEEE Transactions on Audio, Speech, and Language Processing.

[25]  Jirí Mekyska,et al.  Prosodic analysis of neutral, stress-modified and rhymed speech in patients with Parkinson's disease , 2016, Comput. Methods Programs Biomed..

[26]  E. Růžička,et al.  Quantitative acoustic measurements for characterization of speech and voice disorders in early untreated Parkinson's disease. , 2011, The Journal of the Acoustical Society of America.