• Speech Sciences
• /
• 제14권4호
• /
• 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.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.249-252
• /
• 2001

The most basic means of communication among humans is a voice. Without speaking of voice technologies, we found it is important and convenient to use a voice in everyday life. But. in consideration to speech recognition systems, we can't always desire a normal voice input as input signal to the system. Generally speaking. a pathological voice as against a normal which is a voice with a problem in the larynx. could be also special case of input voice. Of course, but the distortion of a speech signal by environmental effects i.e., noise or transmission channel was a raised problem. we will take up a pathological voices with laryngeal disease which is essential distortion factor in voice. Also, we are to find out the difference of acoustic parameters distribution between normal and pathological voice by a statistical method in our research.

• MALSORI
• /
• 제64호
• /
• pp.77-88
• /
• 2007

Nowadays, mel-frequency cesptral coefficients (MFCCs) and Gaussian mixture models (GMMs) are used for the pathological voice detection. This paper suggests a method to improve the performance of the pathological/normal voice classification based on the MFCC-based GMM. We analyze the characteristics of the mel frequency-based filterbank energies using the fisher discriminant ratio (FDR). And the feature vectors through the linear discriminant analysis (LDA) transformation of the filterbank energies (FBE) and the MFCCs are implemented. An accuracy is measured by the GMM classifier. This paper shows that the FBE LDA-based GMM is a sufficiently distinct method for the pathological/normal voice classification, with a 96.6% classification performance rate. The proposed method shows better performance than the MFCC-based GMM with noticeable improvement of 54.05% in terms of error reduction.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1797-1798
• /
• 2007

In field of voice pathology, diverse statistics extracted form pitch estimation were commonly used to assess voice quality. In this study, we proposed robust pitch detection algorithm which can estimate pitch of pathological voices in benign vocal fold lesions. we also compared our proposed algorithm with three established pitch detection algorithms; autocorrelation, simplified inverse filtering technique, and nonlinear state-space embedding methods. In the database of total pathological voices of 99 and normal voices of 30, an analysis of errors related with pitch detection was evaluated between pathological and normal voices, or among the types of pathological voices. According to the results of pitch errors, gross pitch error showed some increases in cases of pathological voices; especially excessive increase in PDA based on nonlinear time-series. In an analysis of types of pathological voices classified by aperiodicity and the degree of chaos, the more voice has aperiodic and chaotic, the more growth of pitch errors increased. Consequently, it is required to survey the severity of tested voice in order to obtain accurate pitch estimates.

• MALSORI
• /
• 제66호
• /
• pp.61-72
• /
• 2008

This paper proposes a method to improve pathological and normal voice classification performance by combining multiple features such as auditory-based and higher-order features. Their performances are measured by Gaussian mixture models (GMMs) and linear discriminant analysis (LDA). The combination of multiple features proposed by the frame-based LDA method is shown to be an effective method for pathological and normal voice classification, with a 87.0% classification rate. This is a noticeable improvement of 17.72% compared to the MFCC-based GMM algorithm in terms of error reduction.

• Speech Sciences
• /
• 제13권3호
• /
• 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/.

• Proceedings of the KSLP Conference
• /
• 대한음성언어의학회 1998년도 제10회 학술대회 심포지움
• /
• 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)

• Speech Sciences
• /
• 제14권1호
• /
• 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.

• Phonetics and Speech Sciences
• /
• 제3권3호
• /
• pp.99-108
• /
• 2011

The perturbation parameters like jitter, shimmer, and signal-to-noise ratio (SNR) are largely estimated in the particular segment from the subjective or whole portion of the given pathological voice signal although there are many possible regions to be able to analyze the voice signals. In this paper, the pathological voice signals were classified as type 1, 2, 3, or 4 according to narrow band spectrogram and the value differences of the perturbation parameters extracted in the subjective and entire portion tended to be getting bigger as from type 1 to type 4 signals. Therefore, sample selection method based on moving window to analyze type 2 and 3 signals as well as type 1 signals is proposed. Although type 3 signals cannot be analyzed using the perturbation analysis, the type 3 signals by selecting out the samples in which error count is less than 10 through moving window were analyzed. At present, there is no method to be able to analyze the type 4 signals. Future research will endeavor to determine the best way to evaluate such voices.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• 제33권3호
• /
• pp.142-155
• /
• 2022

Diagnosis using voice is non-invasive and can be implemented through various voice recording devices; therefore, it can be used as a screening or diagnostic assistant tool for laryngeal voice disease to help clinicians. The development of artificial intelligence algorithms, such as machine learning, led by the latest deep learning technology, began with a binary classification that distinguishes normal and pathological voices; consequently, it has contributed in improving the accuracy of multi-classification to classify various types of pathological voices. However, no conclusions that can be applied in the clinical field have yet been achieved. Most studies on pathological speech classification using speech have used the continuous short vowel /ah/, which is relatively easier than using continuous or running speech. However, continuous speech has the potential to derive more accurate results as additional information can be obtained from the change in the voice signal over time. In this review, explanations of terms related to artificial intelligence research, and the latest trends in machine learning and deep learning algorithms are reviewed; furthermore, the latest research results and limitations are introduced to provide future directions for researchers.