Detection of severe obstructive sleep apnea through voice analysis

This paper deals with the potential and limitations of using voice and speech processing to detect Obstructive Sleep Apnea (OSA). An extensive body of voice features has been extracted from patients who present various degrees of OSA as well as healthy controls. We analyse the utility of a reduced set of features for detecting OSA. We apply various feature selection and reduction schemes (statistical ranking, Genetic Algorithms, PCA, LDA) and compare various classifiers (Bayesian Classifiers, kNN, Support Vector Machines, neural networks, Adaboost). S-fold crossvalidation performed on 248 subjects shows that in the extreme cases (that is, 127 controls and 121 patients with severe OSA) voice alone is able to discriminate quite well between the presence and absence of OSA. However, this is not the case with mild OSA and healthy snoring patients where voice seems to play a secondary role. We found that the best classification schemes are achieved using a Genetic Algorithm for feature selection/reduction.

[1]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[2]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[3]  Y. Qi,et al.  Temporal and spectral estimations of harmonics-to-noise ratio in human voice signals. , 1997, The Journal of the Acoustical Society of America.

[4]  T. Young,et al.  Epidemiology of obstructive sleep apnea: a population health perspective. , 2002, American journal of respiratory and critical care medicine.

[5]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[6]  P. Boersma,et al.  Spectral characteristics of three styles of Croatian folk singing. , 2006, The Journal of the Acoustical Society of America.

[7]  Thomas Bäck,et al.  Extended Selection Mechanisms in Genetic Algorithms , 1991, ICGA.

[8]  Jarek Krajewski,et al.  An Acoustic Framework for Detecting Fatigue in Speech Based Human-Computer-Interaction , 2008, ICCHP.

[9]  Jacques Koreman,et al.  FINDING CORRELATES OF VOCAL FOLD ADDUCTION DEFICIENCIES , 1997 .

[10]  J. A. Scott,et al.  Influence of sex and age on duration and frequency of sleep apnea events. , 2000, Sleep.

[11]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[12]  D. Fogel.  Evolutionary algorithms in theory and practice , 1997, Complex..

[13]  P. Monoson,et al.  Preliminary observation of speech disorder in obstructive and mixed sleep apnea. , 1987, Chest.

[14]  P. Perrier,et al.  A biomechanical model of cardinal vowel production: muscle activations and the impact of gravity on tongue positioning. , 2009, The Journal of the Acoustical Society of America.

[15]  David D. Sampson,et al.  Measurement, Reconstruction, and Flow-Field Computation of the Human Pharynx With Application to Sleep Apnea , 2010, IEEE Transactions on Biomedical Engineering.

[16]  V. Somers,et al.  Obstructive Sleep Apnea , 2005 .

[17]  P. Monoson,et al.  Speech dysfunction of obstructive sleep apnea. A discriminant analysis of its descriptors. , 1989, Chest.

[18]  ThieleLothar,et al.  A comparison of selection schemes used in evolutionary algorithms , 1996 .

[19]  M.G. Bellanger,et al.  Digital processing of speech signals , 1980, Proceedings of the IEEE.

[20]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[21]  T. Baer,et al.  A pitch-synchronous analysis of hoarseness in running speech. , 1988, The Journal of the Acoustical Society of America.

[22]  Max A. Little,et al.  Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection , 2007 .

[23]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[24]  D. Terris,et al.  Screening for obstructive sleep apnea: an evidence-based analysis. , 2006, American journal of otolaryngology.

[25]  Daniel J Buysse,et al.  Sleep–Related Breathing Disorders in Adults: Recommendations for Syndrome Definition and Measurement Techniques in Clinical Research , 2000 .

[26]  Gilbert Syswerda,et al.  Uniform Crossover in Genetic Algorithms , 1989, ICGA.

[27]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[28]  Daniel J Buysse,et al.  Sleep-related breathing disorders in adults: recommendations for syndrome definition and measurement techniques in clinical research. The Report of an American Academy of Sleep Medicine Task Force. , 1999, Sleep.

[29]  G. de Krom.  A cepstrum-based technique for determining a harmonics-to-noise ratio in speech signals. , 1993, Journal of speech and hearing research.

[30]  N J Douglas,et al.  Neck and total body fat deposition in nonobese and obese patients with sleep apnea compared with that in control subjects. , 1998, American journal of respiratory and critical care medicine.

[31]  T. Leino.  Long-term average spectrum in screening of voice quality in speech: untrained male university students. , 2009, Journal of voice : official journal of the Voice Foundation.

[32]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[33]  Luis A. Hernández Gómez,et al.  Improving Automatic Detection of Obstructive Sleep Apnea Through Nonlinear Analysis of Sustained Speech , 2013, Cognitive Computation.

[34]  R. Jané,et al.  Acoustic analysis of vowel emission in obstructive sleep apnea. , 1993, Chest.

[35]  Lothar Thiele,et al.  A Comparison of Selection Schemes Used in Evolutionary Algorithms , 1996, Evolutionary Computation.

[36]  Yaniv Zigel,et al.  Automatic Detection of Obstructive Sleep Apnea Using Speech Signals , 2011, IEEE Transactions on Biomedical Engineering.

[37]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[38]  James C. Bezdek,et al.  A note on self-organizing semantic maps , 1995, IEEE Trans. Neural Networks.

[39]  Guus de Krom,et al.  A Cepstrum-Based Technique for Determining a Harmonics-to-Noise Ratio in Speech Signals , 1993 .

[40]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[41]  M. Littner,et al.  Practice parameters for the indications for polysomnography and related procedures: an update for 2005. , 2005, Sleep.

[42]  E. Bixler,et al.  Effects of age on sleep apnea in men: I. Prevalence and severity. , 1998, American journal of respiratory and critical care medicine.

[43]  Shinobu Masaki,et al.  Difference in vocal tract shape between upright and supine postures: Observations by an open-type MRI scanner , 2005 .

[44]  David G. Stork,et al.  Pattern Classification , 1973 .

[45]  Ronald J. Baken,et al.  Clinical measurement of speech and voice , 1987 .

[46]  Thomas Bäck,et al.  Evolutionary algorithms in theory and practice - evolution strategies, evolutionary programming, genetic algorithms , 1996 .

[47]  Dimitar D. Deliyski,et al.  Acoustic model and evaluation of pathological voice production , 1993, EUROSPEECH.

[48]  D. Jamieson,et al.  Acoustic discrimination of pathological voice: sustained vowels versus continuous speech. , 2001, Journal of speech, language, and hearing research : JSLHR.

[49]  T. Utlaut.  Nonparametric Statistics with Applications to Science and Engineering , 2008 .

[50]  David Talkin,et al.  A Robust Algorithm for Pitch Tracking ( RAPT ) , 2005 .

[51]  K. Scherer,et al.  Effect of experimentally induced stress on vocal parameters. , 1986, Journal of experimental psychology. Human perception and performance.