Vocal Folds Disorder Detection using Pattern Recognition Methods

Abstract

Diagnosis of pathological voice is one of the most important issues in biomedical applications of speech technology. This study focuses on the classification of pathological voice using the HMM(Hidden Markov Model), the GMM(Gaussian Mixture Model) and a SVM (Support Vector Machine), and then compares the results to work done previously using an ANN (Artificial Neural Network). Speech data were collected from those without and those with vocal disorders. Normal and pathological speech data were mixed in out experiment. Six characteristic parameters (Jitter, Shimmer, NHR, SPI, APQ and RAP) were chosen. Then the pattern recognition methods (HMM, GMM and SVM) were used to distinguish the mixed data into categories of normal and pathological speech. We found that the GMM-based method can give us superior classification rates compared to the other classification methods.

Reliable Jitter and Shimmer Measurements in Voice Clinics: The Relevance of Vowel, Gender, Vocal Intensity, and Fundamental Frequency Effects in a Typical Clinical Task

“…16,17 Additionally, correct recognition of pathologic voices has been reported to be as high as above 95% when perturbation parameters are used in combination with a mathematical pattern recognition model. 18 Furthermore, investigations in ''normal'' sounding voices such as in patients with laryngopharyngeal reflux or after thyroid surgery imply that perturbation parameters might even track subtle voice alterations not easily detectable by perceptual or visual assessment methods. 19,20 However, applications of jitter and shimmer analysis have been thwarted by unsatisfactory measurement reliability, sensitivity, and specificity.…”

Recognition of pathological voices by Human Factor Cepstral Coefficients (HFCC)

“…Proper grading will allow automatic diagnosis and treatment of the disease. [1] For several years until now, the detection of vocal pathology can be evaluated in a subjective or objective way [2]. Indeed, the objective evaluation of acoustic signals is done through computer tools.…”

“…the index of the center frequency 1 or M, the coefficients ̅ and ̅ are defined by: constants a, b and c mentioned in(1) are expressed by the following values: 6.23 * 10−6, 93.39 * 10−3 and 28.52 respectively and they vary in both cases, for the first filter, the coefficients , , and ̂ are calculated as follows:Once the center frequencies of the first and last filter are calculated, the generation of the center frequencies of the filters in the middle is easy because they are equidistant on the mel scale, the step  f ∆ between the center frequencies of the filters adjacent is calculated by:…”

Investigation of Voice Pathology Detection and Classification on Different Frequency Regions Using Correlation Functions

“…Binary classifier SVM showed the best results compared with other classifiers, with a recognition rate of 94.26%. In Wang et al [22], MFCC and six acoustic parameters (jitter, shimmer, NHR, SPI, APQ, and Relative Average Perturbation) were extracted, with the results compared with those of the NN-based voice pathology detection system [23].…”