Classification and analysis of speech abnormalities

Abstract Analysis of speech has become a popular non-invasive tool for assessing the speech abnormalities. Acoustic nature of the abnormal speech gives relevant information about the type of disorder in the speech production system. These signals are essentially non-stationary; may contain indicators of current disease, or even warnings about impending diseases. The indicators may be present at all times or may occur at random — during certain intervals of the day. However, to study and pinpoint abnormalities in voluminous data collected over several hours is strenuous and time consuming. Therefore, computer based analytical tools for in-depth study and classification of data over daylong intervals can be very useful in diagnostics. This paper deals with the classification of certain diseases using artificial neural network, and then analyzed. This analysis is carried out using continuous wavelet transformation patterns. The results for various types of subjects discussed in detail and it is evident that the classifier presented in this paper has a remarkable efficiency in the range of 80–85% of accuracy.

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

[2]  Michael A. Crary,et al.  Organic Voice Disorders: Assessment and Treatment , 1996 .

[3]  Jelena Kovacevic,et al.  Wavelets and Subband Coding , 2013, Prentice Hall Signal Processing Series.

[4]  Stamatios V. Kartalopoulos,et al.  Understanding neural networks and fuzzy logic - basic concepts and applications , 1997 .

[5]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[6]  Jagadish Nayak,et al.  Identification of voice disorders using speech samples , 2003, TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region.

[7]  Ph. Tchamitchian,et al.  Wavelets: Time-Frequency Methods and Phase Space , 1992 .

[8]  Ajit S. Bopardikar,et al.  Wavelet transforms - introduction to theory and applications , 1998 .

[9]  平野 実,et al.  Understanding Voice Problems: A Physiological Perspective for Diagnosis and Treatment , 1996 .

[10]  Martin Vetterli,et al.  Wavelets and filter banks: theory and design , 1992, IEEE Trans. Signal Process..

[11]  Fabrice Plante,et al.  Speech monitoring of infective laryngitis , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[12]  C. Chui.  Wavelet Analysis and Its Applications , 1992 .

[13]  L. Gavidia-Ceballos,et al.  Direct speech feature estimation using an iterative EM algorithm for vocal fold pathology detection , 1996, IEEE Transactions on Biomedical Engineering.

[14]  Alison Behrman,et al.  Instrumentation in Voice Assessment and Treatment , 1997 .

[15]  R.P. Lippmann,et al.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[16]  Richard Kronland-Martinet,et al.  Reading and Understanding Continuous Wavelet Transforms , 1989 .

[17]  D. Jamieson,et al.  Identification of pathological voices using glottal noise measures. , 2000, Journal of speech, language, and hearing research : JSLHR.

[18]  Alan V. Oppenheim,et al.  All-pole modeling of degraded speech , 1978 .

[19]  Dae-Hyun Kim,et al.  Analysis of disordered speech signal using wavelet transform , 1998, ICSLP.

[20]  M. Jack,et al.  Robust F/sub 0/ and jitter estimation in pathological voices , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.