Detection of Vocal Cyst Problem by Using High Order Moments and Support Vector Machines

Abstract

The voice disorders occurring due to the problems in the voice producing organs cause some changes in the intensity or tone of the voice. It is difficult to identify the diseased voice by the reason of its variable and different nature. One of the most popular voice disorder reasons is cyst which is located on the vocal cords. The aim of this study is to detect the vocal cyst problem by using acoustic voices data which were recorded from healthy people and patient with cyst diagnoses subjects by using high order statistics and support vector machines (SVMs) classifier. In this study, two experimental procedures were implemented for two different voice samples. In the first, /a/ vowel and the second, the Turkish word of “aydınlık” (mean in English “bright”) were investigated with skewness and kurtosis parameters which are third and fourth order cumulants (spectral moments), respectively. The obtained features values for healthy and cyst subjects were used as the SVMs’ inputs for classification. The experimental results show that the test accuracies of SVMs were found as 94.89% and 91.11% for /a/ vowel and “aydınlık” word, respectively. It is concluded from experimental studies that skewness provides more meaningful results than kurtosis in relation to distinguish into two voice groups as healthy and cyst. Additionally, it is assessed that the “aydınlık” is affective word for the pathological and normal acoustic voice discrimination as good as /a/vowel.

Keywords

• Voice disorders,vocal cords cyst,skewness,kurtosis,support vector machines

Detection of Vocal Cyst Problem by Using High Order Moments and Support Vector Machines

Abstract

The voice disorders occurring due to the problems in the voice producing organs cause some changes in the intensity or tone of the voice. It is difficult to identify the diseased voice by the reason of its variable and different nature. One of the most popular voice disorder reasons is cyst which is located on the vocal cords. The aim of this study is to detect the vocal cyst problem by using acoustic voices data which were recorded from healthy people and patient with cyst diagnoses subjects by using high order statistics and support vector machines (SVMs) classifier. In this study, two experimental procedures were implemented for two different voice samples. In the first, /a/ vowel and the second, the Turkish word of “aydınlık” (mean in English “bright”) were investigated with skewness and kurtosis parameters which are third and fourth order cumulants (spectral moments), respectively. The obtained features values for healthy and cyst subjects were used as the SVMs’ inputs for classification. The experimental results show that the test accuracies of SVMs were found as 94.89% and 91.11% for /a/ vowel and “aydınlık” word, respectively. It is concluded from experimental studies that skewness provides more meaningful results than kurtosis in relation to distinguish into two voice groups as healthy and cyst. Additionally, it is assessed that the “aydınlık” is affective word for the pathological and normal acoustic voice discrimination as good as /a/vowel.

Keywords

• ses bozuklukları,vokal kist,çarpıklık,basıklık,destek vektör makineler

References

1. [1] Lions Voice Clinic. University of Minnesota, Department of Otolaryngology, P.O. Box 487, 420 Delaware St., SE, Minneapolis, MN 55455, USA. Available at: http://www.lionsvoiceclinic.umn.edu
2. [2] Martins R. H. G., Amaral H. A., Tavares E. L. M., Martins M. G., Gonçalves T. M., Dias N. H., “Voice disorders: Etilogy and diagnosis”, Journal of Voice, 30(6):761-769, (2016).
3. [3] Kılıç M. A., “Ses problem olan hastanın objektif ve subjektif yöntemlerle değerlendirilmesi”, CurrPract ORL, 6(2):257-265, (2010).
4. [4] Lovato A., De Colle W., Giacomelli L., Piacente A., Righetto L., Marioni G., Filippis C., “Multi-dimensional voice program (MDVP) vs Praat for assessing euphonic subjects: A preliminary study on the gender-discriminating power of acoustic analysis software”, Journal of Voice, 30(6):765e1-765e5, (2016).
5. [5] Rosa, M.O., Pereira, J.C., Grellet, M. and Carvalho A.C.P.L.F., “Signal processing and statistical procedures to identify laryngeal pathologies”, IEEE International Conference on Electronics, Circuits, and Systems, 1: 423-426, (1999).
6. [6] Arjmandi M. K., Pooyan M., Mikaili M., Vali M., Moqarehzadeh A., “Identification of voice disorders using long-time features and support vector machine with different feature reduction methods”, Journal of Voice, 25(6), e275-e289, (2011).
7. [7] Sonu, Sharma R.K., “Disease detection using analysis of voice parameters”, International Journal of Computing Science and Communication Technologies, 4(2), (2012).
8. [8] Kılıç M. A., “Ses bozuklukları: Yeni bir sınıflandırma sistemi”, Ç. Ü. Tıp Fakültesi Arşiv Kaynak Tarama Dergisi, 8(3):321-337, (1999).

9. [9] Gerçeker M., Yorulmaz İ., Ural A., “Ses ve konuşma”, K.B.B. ve Baş Boyun Cerrahisi Dergisi, 8(1):71-78, (2000).
10. [10] Türk O., Şayli Ö., Özsoy A. S., Arslan L. M., “Türkçe’de ünlülerün formant analizi”, Proceedings of the 18th National Conference in Turkish Linguistics, Ankara, Turkey, (2004). [11] Wang X.,Zhang J., Yan Y., “Discrimination between pathological and normal voices using GMM-SVM approach”, Journal of Voice, 25(1):38-43, (2011).
11. [12] Hadjitodorov S., Mitev P., “A computer system for acoustic analysis of pathological voices and laryngeal diseases screening”, Med. Eng. Phys., 24:419–429, (2002).
12. [13] Arias-Londono J. D., Godino-Llorente J. I., Saenz-Lechon N., Osma-Ruiz V., Castellanos-Dominguez G., “An improved method for voice pathology detection by means of a HMM-based feature space transformation”, Pattern Recognition, 9(43):3100-3112, (2010).
13. [14] Mahmoud I. A., Hanaa S. A., “Wavelet-based Mel frequency cepstral coefficient for speaker identification using hidden markov models”, Journal of Telecommunications, 1 (2):16-21, (2010).
14. [15] Arjmandi M. K., Pooyan M., “An optimum algorithm in pathological voice quality assessment using wavelet-packet-based features, linear discriminant analysis and support vector machine”, Biomedical Signal Processing and Control, 7:3-19, (2012).
15. [16] Eskidere Ö., Aktaş Ö., Ünal C., “Voice disorders identification using discrete wavelet based features”, Medical Technologies National Conference (TIPTEKNO), 15-18 Oct., Bodrum, Turkey, (2015).
16. [17] Alonso J. B., Díaz-de-Maria F., Trivieso C. M., Ferrer M. A., “Using nonlinear features for voice disorder detection,” 3rd Int. Conf. Nonlinear Speech Process, Barcelona, Spain, Apr. pp 94-106, (2005).
17. [18] Muhammad G., Altuwaijri G., Alsulaiman M., Ali Z., Mesallam T. A., Farahat M., Malki K. H., Al-nasheri A., “Automatic voice pathology detection and classification using vocal tract area irregularity”, Biocybernetics and Biomedical Engineering, 36, 309 – 317, (2016).
18. [19] Porat B., Friendlander B., “Direction Finding Algorithms Based on High-Order Statistics”, IEEE Transaction on Signal Processing, 39(9):2016-2024 , (1991).
19. [20] Tanner K., Roy N., Ash A., Buder E. H., “Spectral moments of the long-term average spectrum: sensitive indices of voice change after therapy?”, Journal of Voice, 19(2):211-22, (2005).
20. [21] Lowell, S.Y., Colton, R.H., Kelley, R.T., Hahn, Y.C., “Spectral- and cepstral-based measures during continuous speech: capacity to distinguish dysphonia and consistency within a speaker”, Journal of Voice, 25(5) :223-232, (2011).
21. [22] Nemer E., Goubran R., Mahmoud S., “Robust voice activity detection using higher-order statistics in the LPC residual domain”, IEEE Transaction on Speech and Audio Processing, 9(3):217-231, (2001).
22. [23]Malkoç E., “Türkçe ünlü formant frekans değerleri ve bu değerlere dayalı ünlü dörtgeni”, Dil Dergisi, 146:71-85, (2009).
23. [24] Pearson K., “Contribution to the mathematical theory of evolution, II. Skew variation in homogeneous material”, Philosophical Transactions of the Royal Society of London, 91:343-414, (1895).
24. [25] Fiori A. M., Zenga M., “Karl Pearson and the Origin of Kurtosis”, International Statistical Review, 77(1):40–50, (2009).
25. [26] Vapnik V, “Statistical learning theory”, John Wiley&Sons, New York, (1998).