Comparison of Telephone Recordings and Professional Microphone Recordings for Early Detection of Parkinson's Disease, Using Mel-Frequency Cepstral Coefficients with Gaussian Mixture Models

Vocal impairments are among the earliest symptoms in Parkinson’s Disease (PD). We adapted a method classically used in speech and speaker recognition, based on MelFrequency Cepstral Coefficients (MFCC) extraction and Gaussian Mixture Model (GMM) to detect recently diagnosed and pharmacologically treated PD patients. We classified early PD subjects from controls with an accuracy of 83%, using recordings obtained with a professional microphone. More interestingly, we were able to classify PD from controls with an accuracy of 75 % based on telephone recordings. As far as we know, this is the first time that audio recordings from telephone network have been used for early PD detection. This is a promising result for a potential future telediagnosis of Parkinson's disease.

[1]  Antanas Verikas,et al.  Detecting Parkinson’s disease from sustained phonation and speech signals , 2017, PloS one.

[2]  E. Růžička,et al.  Imprecise vowel articulation as a potential early marker of Parkinson's disease: effect of speaking task. , 2013, The Journal of the Acoustical Society of America.

[3]  Roman Cmejla,et al.  Automatic Evaluation of Articulatory Disorders in Parkinson’s Disease , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[4]  Jesús Francisco Vargas-Bonilla,et al.  Effect of acoustic conditions on algorithms to detect Parkinson's disease from speech , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  M. Breteler,et al.  Epidemiology of Parkinson's disease , 2006, The Lancet Neurology.

[6]  Wenyao Xu,et al.  DeepVoice: A voiceprint-based mobile health framework for Parkinson's disease identification , 2018, 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[7]  P. Bühlmann,et al.  Analyzing Bagging , 2001 .

[8]  Elmar Nöth,et al.  Automatic evaluation of parkinson's speech - acoustic, prosodic and voice related cues , 2013, INTERSPEECH.

[9]  Habib Benali,et al.  Automatic detection of early stages of Parkinson's disease through acoustic voice analysis with mel-frequency cepstral coefficients , 2017, 2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).

[10]  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.

[11]  M. Hoehn,et al.  Parkinsonism , 1967, Neurology.

[12]  Max A. Little,et al.  Using the cellular mobile telephone network to remotely monitor Parkinson ‟ s disease symptom severity , 2022 .

[13]  Alain Ghio,et al.  Measurement of Tremor in the Voices of Speakers with Parkinson's Disease , 2015, ICNLSP.

[14]  Fikret S. Gürgen,et al.  Collection and Analysis of a Parkinson Speech Dataset With Multiple Types of Sound Recordings , 2013, IEEE Journal of Biomedical and Health Informatics.

[15]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[16]  Jing Zhang,et al.  Premotor biomarkers for Parkinson's disease - a promising direction of research , 2012, Translational Neurodegeneration.

[17]  Laetitia Jeancolas,et al.  Analyse de la Voix au Stade Débutant de la Maladie de Parkinson et Corrélations avec Analyse clinique et Neuroimagerie , 2019 .

[18]  Jesús Francisco Vargas-Bonilla,et al.  Characterization Methods for the Detection of Multiple Voice Disorders: Neurological, Functional, and Laryngeal Diseases , 2015, IEEE Journal of Biomedical and Health Informatics.

[19]  Y. Zhang Can a Smartphone Diagnose Parkinson Disease? A Deep Neural Network Method and Telediagnosis System Implementation , 2017, Parkinson's disease.

[20]  E. Růžička,et al.  Evaluation of speech impairment in early stages of Parkinson’s disease: a prospective study with the role of pharmacotherapy , 2013, Journal of Neural Transmission.

[21]  Saudi Arabia,et al.  Automatic Detection of Parkinson's Disease from Words Uttered in Three Different Languages , 2014 .

[22]  Elmar Nöth,et al.  Automatic Detection of Parkinson's Disease Based on Modulated Vowels , 2016, INTERSPEECH.

[23]  Jirí Mekyska,et al.  Identification of hypokinetic dysarthria using acoustic analysis of poem recitation , 2017, 2017 40th International Conference on Telecommunications and Signal Processing (TSP).

[24]  S. Boll,et al.  Suppression of acoustic noise in speech using spectral subtraction , 1979 .

[25]  Michal Novotný,et al.  Smartphone Allows Capture of Speech Abnormalities Associated With High Risk of Developing Parkinson’s Disease , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[26]  Max A. Little,et al.  Novel Speech Signal Processing Algorithms for High-Accuracy Classification of Parkinson's Disease , 2012, IEEE Transactions on Biomedical Engineering.

[27]  Ahmed Hammouch,et al.  Analysis of multiple types of voice recordings in cepstral domain using MFCC for discriminating between patients with Parkinson’s disease and healthy people , 2016, International Journal of Speech Technology.

[28]  Juan Ignacio Godino-Llorente,et al.  MFCC-based Remote Pathology Detection on Speech Transmitted Through the Telephone Channel - Impact of Linear Distortions: Band Limitation, Frequency Response and Noise , 2009, BIOSIGNALS.

[29]  J. Jankovic,et al.  Movement Disorder Society‐sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS‐UPDRS): Process, format, and clinimetric testing plan , 2007, Movement disorders : official journal of the Movement Disorder Society.

[30]  Amit P. Sheth,et al.  Predicting Parkinson's Disease Progression with Smartphone Data , 2013 .

[31]  Juan Ignacio Godino-Llorente,et al.  Automatic Detection of Laryngeal Pathologies in Records of Sustained Vowels by Means of Mel-Frequency Cepstral Coefficient Parameters and Differentiation of Patients by Sex , 2009, Folia Phoniatrica et Logopaedica.

[32]  David Zhang,et al.  Influence of sampling rate on voice analysis for assessment of Parkinson's disease. , 2018, The Journal of the Acoustical Society of America.

[33]  Paul Boersma,et al.  Praat, a system for doing phonetics by computer , 2002 .

[34]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[35]  I. Cobeta,et al.  Acoustic voice analysis in patients with Parkinson's disease treated with dopaminergic drugs. , 1997, Journal of voice : official journal of the Voice Foundation.

[36]  Thomas Quatieri,et al.  Discrete-Time Speech Signal Processing: Principles and Practice , 2001 .

[37]  Max A. Little,et al.  Detecting and monitoring the symptoms of Parkinson's disease using smartphones: A pilot study. , 2015, Parkinsonism & related disorders.

[38]  A. Lang,et al.  How does parkinsonism start? Prodromal parkinsonism motor changes in idiopathic REM sleep behaviour disorder. , 2012, Brain : a journal of neurology.

[39]  Canan Ozsancak,et al.  Treatments for dysarthria in Parkinson's disease , 2004, The Lancet Neurology.