The identification and classification of pathological voice are still a challenging area of research in speech processing. Acoustic features of speech are used mainly to discriminate normal voices from pathological vo...The identification and classification of pathological voice are still a challenging area of research in speech processing. Acoustic features of speech are used mainly to discriminate normal voices from pathological voices. This paper explores and compares various classification models to find the ability of acoustic parameters in differentiating normal voices from pathological voices. An attempt is made to analyze and to discriminate pathological voice from normal voice in children using different classification methods. The classification of pathological voice from normal voice is implemented using Support Vector Machine (SVM) and Radial Basis Functional Neural Network (RBFNN). The normal and pathological voices of children are used to train and test the classifiers. A dataset is constructed by recording speech utterances of a set of Tamil phrases. The speech signal is then analyzed in order to extract the acoustic parameters such as the Signal Energy, pitch, formant frequencies, Mean Square Residual signal, Reflection coefficients, Jitter and Shimmer. In this study various acoustic features are combined to form a feature set, so as to detect voice disorders in children based on which further treatments can be prescribed by a pathologist. Hence, a successful pathological voice classification will enable an automatic non-invasive device to diagnose and analyze the voice of the patient.展开更多
The purpose of this study was to investigate to what extent age and gender would affect the voice parameters of native Mandarin Chinese speakers.Participants were required to produce sustained vowel/a/with comfortable...The purpose of this study was to investigate to what extent age and gender would affect the voice parameters of native Mandarin Chinese speakers.Participants were required to produce sustained vowel/a/with comfortable pitch and loudness.From the speech samples,34 voice parameters were extracted by using Multi-Dimensional Voice Program(MDVP).The parameters were divided into several groups according to their correlation coefficients.Groups related to F0,to short-term perturbation of period and amplitude,to long-term variation of period and amplitude,to spectrum and to duration were found to be affected by age and gender.In each of them,one of the most important parameters was selected to represent the variation tendency with gender and age.Therefore,to estimate the degree of a voice deviation from normal,the factors of age and gender should be considered.The mean and variance of the parameters were given in this paper,and were compared according to their gender and age.Finally,a normative voice database was constructed for the reference of dysphonia diagnosis for Chinese.展开更多
文摘The identification and classification of pathological voice are still a challenging area of research in speech processing. Acoustic features of speech are used mainly to discriminate normal voices from pathological voices. This paper explores and compares various classification models to find the ability of acoustic parameters in differentiating normal voices from pathological voices. An attempt is made to analyze and to discriminate pathological voice from normal voice in children using different classification methods. The classification of pathological voice from normal voice is implemented using Support Vector Machine (SVM) and Radial Basis Functional Neural Network (RBFNN). The normal and pathological voices of children are used to train and test the classifiers. A dataset is constructed by recording speech utterances of a set of Tamil phrases. The speech signal is then analyzed in order to extract the acoustic parameters such as the Signal Energy, pitch, formant frequencies, Mean Square Residual signal, Reflection coefficients, Jitter and Shimmer. In this study various acoustic features are combined to form a feature set, so as to detect voice disorders in children based on which further treatments can be prescribed by a pathologist. Hence, a successful pathological voice classification will enable an automatic non-invasive device to diagnose and analyze the voice of the patient.
基金supported by the National Social Science Foundation of China(No.18BYY189)Major projects of Ministry of Education of China(No.17JJD740001).
文摘The purpose of this study was to investigate to what extent age and gender would affect the voice parameters of native Mandarin Chinese speakers.Participants were required to produce sustained vowel/a/with comfortable pitch and loudness.From the speech samples,34 voice parameters were extracted by using Multi-Dimensional Voice Program(MDVP).The parameters were divided into several groups according to their correlation coefficients.Groups related to F0,to short-term perturbation of period and amplitude,to long-term variation of period and amplitude,to spectrum and to duration were found to be affected by age and gender.In each of them,one of the most important parameters was selected to represent the variation tendency with gender and age.Therefore,to estimate the degree of a voice deviation from normal,the factors of age and gender should be considered.The mean and variance of the parameters were given in this paper,and were compared according to their gender and age.Finally,a normative voice database was constructed for the reference of dysphonia diagnosis for Chinese.
