Conference Paper

Discrete wavelet transform and support vector machine applied to pathological voice signals identification

Sch. of Eng. of Sao Carlos, Sao Paulo Univ., Sao Carlos, Brazil;
DOI: 10.1109/ISM.2005.50 Conference: Multimedia, Seventh IEEE International Symposium on
Source: IEEE Xplore

ABSTRACT An algorithm able to classify pathological and normal voice signals based on Daubechies discrete wavelet transform (DWT-db) and support vector machines (SVM) classifier is presented. DWT-db is used for time-frequency analysis giving quantitative evaluation of signal characteristics to identify pathologies in voice signals, particularly nodules in vocal folds, of subjects with different ages for both male and female. After using a linear prediction coefficients (LPC) filter, the signals mean square values of a particular scale from wavelet analysis are entries to a nonlinear least square support vector machine (LS-SVM) classifier, which leads to an adequate larynx pathology classifier which over 95% of classification accuracy.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Wavelet kernels have been introduced for both support vector regression and classification. Most of these wavelet kernels do not use the inner product of the embedding space, but use wavelets in a similar fashion to radial basis function kernels. Wavelet analysis is typically carried out on data with a temporal or spatial relation between consecutive data points. We argue that it is possible to order the features of a general data set so that consecutive features are statistically related to each other, thus enabling us to interpret the vector representation of an object as a series of equally or randomly spaced observations of a hypothetical continuous signal. By approximating the signal with compactly supported basis functions and employing the inner product of the embedding L<sub>2</sub> space, we gain a new family of wavelet kernels. Empirical results show a clear advantage in favor of these kernels.
    IEEE Transactions on Pattern Analysis and Machine Intelligence 11/2011; · 4.80 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Early diagnosis of different maladies and pathologies of human vocal system using noninvasive methods and diverse signal processing technics is a problem that is particularly considered by biomedical engineering and signal processing researchers, recently. Automatic detection of voice pathology from speech signal is a new topic and has not been progressed enough. An algorithm able to classify two pathological voice signals based on wavelet packets (WP) and Fisher's linear discriminant (FLD) is presented in this research. We use WP and different mother wavelets (Daubechies, Coiflet, and Symmlet) for time-frequency analysis giving quantitative evaluation of signal characteristics to identify pathologies in voice signals of subjects with different ages for both male and female. Choosing Coiflet mother wavelet, we use FLD to find the best tree among Coiflet Wavelet Packet trees. After selecting best features from terminal nodes of the best tree with contribution to genetic algorithm, we apply support vector machines to separate voice pathologies. Applying our algorithm to seperate polyp from some other pathologies we come to much higher conclusions in contrast to previous works that use Daubechies mother wavelet instead of Coiflet mother wavelet (e.g. 92.5% in comparison to 82.5% for separating polyp from adductor spasmodic dysphonia).
    Computer, Control and Communication, 2009. IC4 2009. 2nd International Conference on; 03/2009
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper an efficient fuzzy wavelet packet (WP) based feature extraction method and fuzzy logic based disorder assessment technique were used to investigate voice signals of patients suffering from unilateral vocal fold paralysis (UVFP). Mother wavelet function of tenth order Daubechies (d10) was employed to decompose signals in 5 levels. Next, WP coefficients were used to measure energy and Shannon entropy features at different spectral sub-bands. Consequently, using fuzzy c-means method, signals were clustered into 2 classes. The amount of fuzzy membership of pathological and normal signals in their corresponding clusters was considered as a measure to quantify the discrimination ability of features. A classification accuracy of 100 percent was achieved using an artificial neural network classifier. Finally, fuzzy c-means clustering method was used as a way of voice pathology assessment. Accordingly, fuzzy membership function based health index is proposed.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 01/2009; 2009:328-31.