• Speech Sciences
• /
• v.4 no.2
• /
• pp.17-24
• /
• 1998

In this paper a method to diagnose pathological voices using wavelet transform is sug gested. Pathological voices are collected from hospital and analyzed by the suggested method. Normal voices are collected separately and analyzed. Then the results are compared to find the differences in their characteristics. Three level wavelet transform is used. Normalized energy ratios between the levels and normalized peak-to-peak values are used as parameters. As a result, it was possible to distinguish between normal and pathological voices.

• Speech Sciences
• /
• v.5 no.1
• /
• pp.151-165
• /
• 1999

This paper describes a series of researches to diagnose vocal diseases using the statistical method and the acoustic signal analysis method. Speech materials are collected at the hospital. Using the pathological database, the basic parameters for the diagnosis are obtained. Based on the statistical characteristics of the parameters, valid parameters are chosen and those are used to diagnose the pathological speech signal. Cepstrum is used to extract parameters which represents characteristics of pathological speech. 3 layered neural network is used to train and classify pathological speech into normal, benign and malignant case.

• Speech Sciences
• /
• v.13 no.3
• /
• pp.7-18
• /
• 2006

Diagnosis of pathological voice is one of the important issues in biomedical applications of speech technology. This study focuses on the discrimination of voice disorder using HMM (Hidden Markov Model) for automatic detection between normal voice and vocal fold disorder voice. This is a non-intrusive, non-expensive and fully automated method using only a speech sample of the subject. Speech data from normal people and patients were collected. Mel-frequency filter cepstral coefficients (MFCCs) were modeled by HMM classifier. Different states (3 states, 5 states and 7 states), 3 mixtures and left to right HMMs were formed. This method gives an accuracy of 93.8% for train data and 91.7% for test data in the discrimination of normal and vocal fold disorder voice for sustained /a/.

• Speech Sciences
• /
• v.14 no.4
• /
• pp.179-200
• /
• 2007

In voice pathology, various measurements calculated from pitch values are proposed to show voice quality. However, those measurements frequently seem to be inaccurate and unreliable because they are based on some wrong pitch values determined from pathological voice data. In order to solve the problem, we compared several pitch estimation methods to propose a better one in pathological voices. From the database of 99 pathological voice and 30 normal voice data, errors derived from pitch estimation were analyzed and compared between pathological and normal voice data or among the vowels produced by patients with benign vocal fold lesions. Results showed that gross pitch errors were observed in the cases of pathological voice data. From the types of pathological voices classified by the degree of aperiodicity in the speech signals, we found that pitch errors were closely related to the number of aperiodic segments. Also, the autocorrelation approach was found to be the most robust pitch estimation in the pathological voice data. It is desirable to conduct further research on the more severely pathological voice data in order to reduce pitch estimation errors.

• Speech Sciences
• /
• v.14 no.1
• /
• pp.151-162
• /
• 2007

This study focuses on the classification of pathological voice using GMM (Gaussian Mixture Model) and compares the results to the previous work which was done by ANN (Artificial Neural Network). Speech data from normal people and patients were collected, then diagnosed and classified into two different categories. Six characteristic parameters (Jitter, Shimmer, NHR, SPI, APQ and RAP) were chosen. Then the classification method based on the artificial neural network and Gaussian mixture method was employed to discriminate the data into normal and pathological speech. The GMM method attained 98.4% average correct classification rate with training data and 95.2% average correct classification rate with test data. The different mixture number (3 to 15) of GMM was used in order to obtain an optimal condition for classification. We also compared the average classification rate based on GMM, ANN and HMM. The proper number of mixtures on Gaussian model needs to be investigated in our future work.

• Proceedings of the KSLP Conference
• /
• 1998.11a
• /
• pp.208-209
• /
• 1998

It is generally known that many cases of pathological rough voice are characterized not by simple random perturbations but by quasi-periodic perturbations in the speech wave. However, there are few studies on the characteristics of perturbations in vocal fold vibrations associated with this type of voice. We have been conducting studies of pathological vocal fold vibration using a high-speed digital image recording system developed by our institute, Compared to the ordinary high-speed-motion picture system, the present system is compact and simple to operate and thus, it suited for pathological data collection. (omitted)

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.123-126
• /
• 2007

This paper suggests a method to improve the performance of the pathological/normal voice classification. The effectiveness of the mel frequency-based filter bank energies using the fisher discriminant ratio (FDR) is analyzed. And mel frequency cepstrum coefficients (MFCCs) and the feature vectors through the linear discriminant analysis (LDA) transformation of the filter bank energies (FBE) are implemented. This paper shows that the FBE LDA-based GMM is more distinct method for the pathological/normal voice classification than the MFCC-based GMM.

• Speech Sciences
• /
• v.11 no.1
• /
• pp.21-29
• /
• 2004

In this paper we examined the effect of normalization on discriminating the pathological voice into normal and abnormal classes using artificial neural network. Average values per each parameter were used to normalize each set of parameter values. Artificial neural networks were used as classifiers. And the effect of normalization was evaluated by comparing the discrimination results between original and normalized parameter sets.

• Speech Sciences
• /
• v.8 no.2
• /
• pp.61-71
• /
• 2001

Speech material, which is collected from ARS(Automatic Response System), was analyzed and classified into disease and non-disease state. The material include 11 different kinds of diseases. Along with ARS speech, DAT(Digital Audio Tape) speech is collected in parallel to give the bench mark. To analyze speech material, analysis tools, which is developed local laboratory, are used to provide an improved and robust performance to the obtained parameters. To classify speech into disease and non-disease class, multi-layered neural network was used. Three different combinations of 3, 6, 12 parameters are tested to obtain the proper network size and to find the best performance. From the experiment, the classification rate of 92.5% was obtained.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.107-115
• /
• 2003

In this paper we tried to classify the pathological voice signal with severe noise component based on two different parameters, the spectral slope and the ratio of energies in the harmonic and noise components (HNR), The spectral slope is obtained by using a curve fitting method and the HNR is computed in cepstrum quefrency domain. Speech data from normal peoples and patients are collected, diagnosed and divided into three different classes (normal, relatively less noisy and severely noisy data), The mean values and the standard deviations of the spectral slope and the HNR are computed and compared with in the three kinds of data to characterize and classify the severely noisy pathological voice signals from others.