A Comparative Study of Pathological Voice Based on Traditional Acoustic Characteristics and Nonlinear Features_Journal of Biomedical Engineering

Authors：

GANDeying ,  HUWeiping , ZHAOBingxin

Electronic Engineering College, Guangxi Normal University, Guilin 541004, China;

Corresponding?author：

HUWeiping, Email: huwp@gxnu.edu.cn

Keywords：

pathological voice; support vector machine; traditional acoustic feature; nonlinear dynamics technology

DOI：

10.7507/1001-5515.20140217

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

By analyzing the mechanism of pronunciation, traditional acoustic parameters, including fundamental frequency, Mel frequency cepstral coefficients (MFCC), linear prediction cepstrum coefficient (LPCC), frequency perturbation, amplitude perturbation, and nonlinear characteristic parameters, including entropy (sample entropy, fuzzy entropy, multi-scale entropy), box-counting dimension, intercept and Hurst, are extracted as feature vectors for identification of pathological voice. Seventy-eight normal voice samples and 73 pathological voice samples for /a/, and 78 normal samples and 80 pathological samples for /i/ are recognized based on support vector machine (SVM). The results showed that compared with traditional acoustic parameters, nonlinear characteristic parameters could be well used to distinguish between healthy and pathological voices, and the recognition rates for /a/ were all higher than those for /i/ except for multi-scale entropy. That is why the /a/ sound data is used widely in related research at home and abroad for obtaining better identification of pathological voices. Adopting multi-scale entropy for /i/ could obtain higher recognition rate than /a/ between healthy and pathological samples, which may provide some useful inspiration for evaluating vocal compensatory function.

Citation： GANDeying, HUWeiping, ZHAOBingxin. A Comparative Study of Pathological Voice Based on Traditional Acoustic Characteristics and Nonlinear Features. Journal of Biomedical Engineering, 2014, 31(5): 1149-1154. doi: 10.7507/1001-5515.20140217 Copy

1.	胡維平,王修信,曾恩恩,等.噪音頻域分析中的特征研究[J]. 廣西物理,1998, 19(1):30-33.
2.	MARKAKI M, STYLIANOU Y. Voice pathology detection and discrimination based on modulation spectral features [J]. IEEE Trans Audio Speech Language Process,2011, 19(7): 1938-1948.
3.	于燕平,胡維平. 病態嗓音特征的小波變換提取及識別研究[J]. 計算機工程與應用, 2009, 45(22): 194-196,205.
4.	高俊芬,胡維平. 基于非線性動力學和高斯混合模型/支持向量機的病態嗓音識別與研究[J]. 生物醫學工程學雜志, 2012, 29(4): 750-753, 759.
5.	OROZCO J R, VARGAS J F, ALONSO J B, et al. Voice pathology detection in continuous speech using nonlinear dynamics[C]//The 11th International Conference on Information Sciences, Signal Processing and their Application. Montreal: 2012: 1030-1033.
6.	GAO J, YU Y, HU W. Recognition of pathological voices based on fractal theory using Gaussian mixture model[C]//The 2010 International Conference on Information, Electronic and Computer Science. Guilin,China: 2010:1668-1671.
7.	HARTL D M, HANS S, VAISSIèRE J, et al. Objective voice quality analysis before and after onset of unilateral vocal fold paralysis [J]. J Voice, 2010, 15(3): 351-361.
8.	TING H N, CHIA S Y, KIM K S, et al. Vocal fundamental frequency and perturbation measurements of vowels by normal malaysian Chinese Adults[J].J Voice,2011,25(6):e311-e317.
9.	龔英姬,胡維平. 基于HHT變換的病態嗓音特征提取及識別研究[J]. 計算機工程與應用, 2007, 43(34):217-219.
10.	王修信,胡維平,姚鐵鈞,等. 頻率微擾熵在正常與病態嗓音聲譜分析中的應用[J]. 廣西師范大學學報,1998,16(4):7-10.
11.	毛大偉, 曹華, 木拉提·哈米提, 等. 基于梅爾倒譜系數和復雜性的說話人識別[J]. 生物醫學工程學雜志, 2006, 23(4):882-886.
12.	KILIC M A, OGVT F, DURSUN G, et al. The effects of vowels on voice pertur-bation measures[J]. J Voice, 2004, 18(3): 318-324.
13.	RICHMAN J S, MOORMAN J R. Physiological time-series analysis using approximate entropy and sample entropy [J]. Am J Physiol Heart Circ Physiol, 2000, 278(6):H2039-H2049.
14.	PINCUS S M. Approximate entropy as a measure of system complexity [J]. Proc Nati Acad Sci U S A,1991, 88(6):2297-2301.
15.	COSTA M, GOLDBERGER A L, PENG C K. Multiscale entropy analysis of complex physiologic time series [J].Phys Rev Lett, 2002, 89(6): 1-4.
16.	VOICU I, GIRAULT J M. Multi-scale similarity entropy as a new descriptor to differentiate healthy to suffering foetus[C]//International Conference on Complex Systems. Agadir: 2012:1-4.
17.	CHEN W T, ZHANG J, YU W X. Measuring complexity using FuzzyEn, ApEn, and SampEn [J].MedEng Phys, 2009, 31(1):61-68.
18.	鄒曉陽, 雷敏. 基于多尺度模糊熵的動作表面肌電信號模式識別[J]. 生物醫學工程學雜志, 2012, 29(6):1184-1188.
19.	HENRíQUEZ P, ALONSO J B, FERRER M A, et al. Characterization of healthy and pathological voice through measures based on nonlinear dynamics[J]. IEEE Trans Audio Speech Language Process, 2009, 17(6):1186-1195.
20.	ZHAO G H, HAO M . Incremental learning algorithm of least squares support vector machines based on Renyi entropy [C]//International Conference on Management Science and Engineering. Moscow: 2009:95-100.
21.	THOMPSON C, MULPUR A , MEHTA V, et al. Trandition to chaos in acoustically driven flows[J]. J Acoust Soc Am, 1991, 90(4): 2097-2103.
22.	焦青, 郭永新, 張正國. 混沌與分形及其在心電信號研究中的應用[J]. 生物醫學工程學雜志,2009, 26(3):676-680.
23.	高俊芬, 胡維平. 基于非線性動力學和GMM的病態嗓音識別與研究[J].廣西師范大學學報(自然科學版), 2011, 29(3): 5-8.
24.	TAKEO F. Box-counting dimension of graphs of generalized takagi series [J]. Japan J Indust Appl, 1996,13: 187-194.
25.	YE X, XIA X, ZHANG J, et al. Effects of trends and seasonalities on robustness of the Hurst parameter estimators [J]. IET Signal Process, 2012, 6(9): 849-856.
26.	VAZIRI G, ALMASGANJ F, JENABI M S. On the fractal self-similarity of laryngeal pathologies detection: the estimation of Hurst parameter [C]//Information Technology and Applications in Biomedicine. Shenzhen: 2008 : 383-386.
27.	CHEN W X, PENG C E, ZHU X, et al. SVM based identification of pathological voices[C]//29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007. Lyon, France: 2007:3786-3789.

1. 胡維平,王修信,曾恩恩,等.噪音頻域分析中的特征研究[J]. 廣西物理,1998, 19(1):30-33.
2. MARKAKI M, STYLIANOU Y. Voice pathology detection and discrimination based on modulation spectral features [J]. IEEE Trans Audio Speech Language Process,2011, 19(7): 1938-1948.
3. 于燕平,胡維平. 病態嗓音特征的小波變換提取及識別研究[J]. 計算機工程與應用, 2009, 45(22): 194-196,205.
4. 高俊芬,胡維平. 基于非線性動力學和高斯混合模型/支持向量機的病態嗓音識別與研究[J]. 生物醫學工程學雜志, 2012, 29(4): 750-753, 759.
5. OROZCO J R, VARGAS J F, ALONSO J B, et al. Voice pathology detection in continuous speech using nonlinear dynamics[C]//The 11th International Conference on Information Sciences, Signal Processing and their Application. Montreal: 2012: 1030-1033.
6. GAO J, YU Y, HU W. Recognition of pathological voices based on fractal theory using Gaussian mixture model[C]//The 2010 International Conference on Information, Electronic and Computer Science. Guilin,China: 2010:1668-1671.
7. HARTL D M, HANS S, VAISSIèRE J, et al. Objective voice quality analysis before and after onset of unilateral vocal fold paralysis [J]. J Voice, 2010, 15(3): 351-361.
8. TING H N, CHIA S Y, KIM K S, et al. Vocal fundamental frequency and perturbation measurements of vowels by normal malaysian Chinese Adults[J].J Voice,2011,25(6):e311-e317.
9. 龔英姬,胡維平. 基于HHT變換的病態嗓音特征提取及識別研究[J]. 計算機工程與應用, 2007, 43(34):217-219.
10. 王修信,胡維平,姚鐵鈞,等. 頻率微擾熵在正常與病態嗓音聲譜分析中的應用[J]. 廣西師范大學學報,1998,16(4):7-10.
11. 毛大偉, 曹華, 木拉提·哈米提, 等. 基于梅爾倒譜系數和復雜性的說話人識別[J]. 生物醫學工程學雜志, 2006, 23(4):882-886.
12. KILIC M A, OGVT F, DURSUN G, et al. The effects of vowels on voice pertur-bation measures[J]. J Voice, 2004, 18(3): 318-324.
13. RICHMAN J S, MOORMAN J R. Physiological time-series analysis using approximate entropy and sample entropy [J]. Am J Physiol Heart Circ Physiol, 2000, 278(6):H2039-H2049.
14. PINCUS S M. Approximate entropy as a measure of system complexity [J]. Proc Nati Acad Sci U S A,1991, 88(6):2297-2301.
15. COSTA M, GOLDBERGER A L, PENG C K. Multiscale entropy analysis of complex physiologic time series [J].Phys Rev Lett, 2002, 89(6): 1-4.
16. VOICU I, GIRAULT J M. Multi-scale similarity entropy as a new descriptor to differentiate healthy to suffering foetus[C]//International Conference on Complex Systems. Agadir: 2012:1-4.
17. CHEN W T, ZHANG J, YU W X. Measuring complexity using FuzzyEn, ApEn, and SampEn [J].MedEng Phys, 2009, 31(1):61-68.
18. 鄒曉陽, 雷敏. 基于多尺度模糊熵的動作表面肌電信號模式識別[J]. 生物醫學工程學雜志, 2012, 29(6):1184-1188.
19. HENRíQUEZ P, ALONSO J B, FERRER M A, et al. Characterization of healthy and pathological voice through measures based on nonlinear dynamics[J]. IEEE Trans Audio Speech Language Process, 2009, 17(6):1186-1195.
20. ZHAO G H, HAO M . Incremental learning algorithm of least squares support vector machines based on Renyi entropy [C]//International Conference on Management Science and Engineering. Moscow: 2009:95-100.
21. THOMPSON C, MULPUR A , MEHTA V, et al. Trandition to chaos in acoustically driven flows[J]. J Acoust Soc Am, 1991, 90(4): 2097-2103.
22. 焦青, 郭永新, 張正國. 混沌與分形及其在心電信號研究中的應用[J]. 生物醫學工程學雜志,2009, 26(3):676-680.
23. 高俊芬, 胡維平. 基于非線性動力學和GMM的病態嗓音識別與研究[J].廣西師范大學學報(自然科學版), 2011, 29(3): 5-8.
24. TAKEO F. Box-counting dimension of graphs of generalized takagi series [J]. Japan J Indust Appl, 1996,13: 187-194.
25. YE X, XIA X, ZHANG J, et al. Effects of trends and seasonalities on robustness of the Hurst parameter estimators [J]. IET Signal Process, 2012, 6(9): 849-856.
26. VAZIRI G, ALMASGANJ F, JENABI M S. On the fractal self-similarity of laryngeal pathologies detection: the estimation of Hurst parameter [C]//Information Technology and Applications in Biomedicine. Shenzhen: 2008 : 383-386.
27. CHEN W X, PENG C E, ZHU X, et al. SVM based identification of pathological voices[C]//29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007. Lyon, France: 2007:3786-3789.

Previous Article
Enhancement and Assessment of the Fundus Image
Next Article
Recent Progress of Research and Applications of Fractal and Its Theories in Medicine

Journal of Biomedical Engineering

A Comparative Study of Pathological Voice Based on Traditional Acoustic Characteristics and Nonlinear Features

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content