A machine learning approach for voice pathology detection using mode decomposition-based acoustic cepstral features

Özkan Arslan

doi:10.53391/mmnsa.1473574

EN

A machine learning approach for voice pathology detection using mode decomposition-based acoustic cepstral features

Abstract

In this paper, a mode decomposition analysis-based adaptive approach is proposed to provide high diagnostic performance for automated voice pathology detection systems. The aim of the study is to develop a reliable and effective system using adaptive cepstral domain features derived from the empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and complete empirical mode decomposition with adaptive noise (CEEMDAN) methods. The descriptive feature sets are obtained by applying mel-frequency cepstral coefficients (MFCCs) and their derivatives, linear predictive coefficients (LPCs) and linear predictive cepstral coefficients (LPCCs) techniques to each decomposition level. The class-balanced data are generated on the VOice ICar fEDerico II database samples using the synthetic minority oversampling technique (SMOTE). The ReliefF algorithm is used to select the most effective and distinctive features. A combination of selected features and a support vector machine (SVM) classifier is used to identify pathological voices. In the pathology detection approach, the results show that the cepstral features based on EMD and SVM-cubic achieves the highest performance with 99.85\% accuracy, 99.85\% F1-score and 0.997 Matthews correlation coefficient (MCC). In pathology-type classification, the cepstral features based on EEMD and SVM-quadratic approach provided the highest performance with 96.49\% accuracy, 96.46\% F1 and 0.949 MCC values. The comprehensive results of this study reveal that mode decomposition-based approaches are more successful and effective than traditional methods for detection and classification of pathological voices.

Keywords

Voice pathology, SMOTE algorithm, mode decomposition, cepstral-domain coefficients, ReliefF algorithm, support vector machine

References

[1] Hegde, S., Shetty, S., Rai, S. and Dodderi, T. A survey on machine learning approaches for automatic detection of voice disorders. Journal of Voice, 33(6), 947.e11-947.e33, (2019).
[2] Ding, H., Gu, Z., Dai, P., Zhou, Z., Wang, L. and Wu, X. Deep connected attention (DCA) ResNet for robust voice pathology detection and classification. Biomedical Signal Processing and Control, 70, 102973, (2021).
[3] Verde, L., De Pietro, G. and Sannino, G. Voice disorder identification by using machine learning techniques. IEEE Access, 6, 16246-16255, (2018).
[4] Islam, R., Abdel-Raheem, E. and Tarique, M. Voice pathology detection using convolutional neural networks with electroglottographic (EGG) and speech signals. Computer Methods and Programs in Biomedicine Update, 2, 100074, (2022).
[5] Chen, L. and Chen, J. Deep neural network for automatic classification of pathological voice signals. Journal of Voice, 36(2), 288.e15-288.e24, (2022).
[6] Al-Nasheri, A., Muhammad, G., Alsulaiman, M., Ali, Z., Mesallam, T.A., Farahat, M. et al. An investigation of multidimensional voice program parameters in three different databases for voice pathology detection and classification. Journal of Voice, 31(1), 113.e9-113.e18, (2017).
[7] Brockmann, M., Drinnan, M.J., Storck, C. and Carding, P.N. Reliable jitter and shimmer measurements in voice clinics: the relevance of vowel, gender, vocal intensity, and fundamental frequency effects in a typical clinical task. Journal of Voice, 25(1), 44-53, (2011).
[8] Ferrand, C.T. Harmonics-to-noise ratio: an index of vocal aging. Journal of Voice, 16(4), 480-487, (2002).
[9] Neto, B.G.A., Fechine, J.M., Costa, S.C. and Muppa, M. Feature estimation for vocal fold edema detection using short-term cepstral analysis. In Proceedings, IEEE 7th International Symposium on BioInformatics and BioEngineering, pp. 1158-1162, Boston, USA, (2007, October).
[10] Gelzinis, A., Verikas, A. and Bacauskiene, M. Automated speech analysis applied to laryngeal disease categorization. Computer Methods and Programs in Biomedicine, 91(1), 36-47, (2008).

[11] Anusuya, M.A. and Katti, S.K. Front end analysis of speech recognition: a review. International Journal of Speech Technology, 14, 99-145, (2011).
[12] Al-Dhief, F.T., Baki, M.M., Latiff, N.M.A.A., Malik, N.N.N.A., Salim, N.S., Albader, M.A.A. Voice pathology detection and classification by adopting online sequential extreme learning machine. IEEE Access, 9, 77293-77306, (2021).
[13] Jothilakshmi, S. Automatic system to detect the type of voice pathology. Applied Soft Computing, 21, 244-249, (2014).
[14] Majidnezhad, V. and Kheidorov, I. An ANN-based method for detecting vocal fold pathology. ArXiv Areprint, ArXiv:1302.1772, (2013).
[15] Chen, L., Wang, C., Chen, J., Xiang, Z. and Hu, X. Voice disorder identification by using Hilbert-Huang transform (HHT) and K nearest neighbor (KNN). Journal of Voice, 35(6), 932.e1- 932.e11, (2021).
[16] Hemmerling, D., Skalski, A. and Gajda, J. Voice data mining for laryngeal pathology assessment. Computers in Biology and Medicine, 69, 270-276, (2016).
[17] Ali, Z., Alsulaiman, M., Elamvazuthi, I., Muhammad, G., Mesallam, T.A., Farahat, M. and Malki, K.H. Voice pathology detection based on the modified voice contour and SVM. Biologically Inspired Cognitive Architectures, 15, 10-18, (2016).
[18] Akbari, A. and Arjmandi, M.K. An efficient voice pathology classification scheme based on applying multi-layer linear discriminant analysis to wavelet packet-based features. Biomedical Signal Processing and Control, 10, 209-223, (2014).
[19] Hammami, I., Salhi, L. and Labidi, S. Voice pathologies classification and detection using EMD-DWT analysis based on higher order statistic features. Irbm, 41(3), 161-171, (2020).
[20] Wu, H., Soraghan, J., Lowit, A. and Di Caterina, G. Convolutional neural networks for pathological voice detection. In Proceedings, 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1-4, Honolulu, Hawaii, USA, (2018, July).
[21] Abdulmajeed, N.Q., Al-Khateeb, B. and Mohammed, M.A. Voice pathology identification system using a deep learning approach based on unique feature selection sets. Expert Systems, 42(1), e13327, (2023).
[22] Chaiani, M., Selouani, S.A., Boudraa, M. and Yakoub, M.S. Voice disorder classification using speech enhancement and deep learning models. Biocybernetics and Biomedical Engineering, 42(2), 463-480, (2022).
[23] Cesari, U., De Pietro, G., Marciano, E., Niri, C., Sannino, G. and Verde, L. A new database of healthy and pathological voices. Computers & Electrical Engineering, 68, 310-321, (2018).
[24] Huang, N.E. Introduction to Hilbert-Huang transform and some recent developments. In The Hilbert-Huang Transform in Engineering, (pp. 1-23). CRC Press, USA, (2005).
[25] Arslan, Ö. and Karhan, M. Effect of Hilbert-Huang transform on classification of PCG signals using machine learning. Journal of King Saud University-Computer and Information Sciences, 34(10), 9915-9925, (2022).
[26] Zhang, T., Zhang, Y., Sun, H. and Shan, H. Parkinson disease detection using energy direction features based on EMD from voice signal. Biocybernetics and Biomedical Engineering, 41(1), 127-141, (2021).
[27] Zhaohua Wu, N.E.H. Ensemble empirical mode decomposition: A noise-assited. Biomed Tech, 55, 193-201, (2010).
[28] Torres, M.E., Colominas, M.A., Schlotthauer, G. and Flandrin, P. A complete ensemble empirical mode decomposition with adaptive noise. In Proceedings, IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 4144-4147, Prague, Czech Republic, (2011, May).
[29] Chen, X., Hu, M. and Zhai, G. Cough detection using selected informative features from audio signals. In Proceedings, 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) pp. 1-6, Shanghai, China, (2021, October).
[30] Ghoraani, B. and Krishnan, S. Time-frequency matrix feature extraction and classification of environmental audio signals. IEEE Transactions on Audio, Speech, and Language Processing, 19(7), 2197-2209, (2011).
[31] Fang, S.H., Tsao, Y., Hsiao, M.J., Chen, J.Y., Lai, Y.H., Lin, F.C. and Wang, C.T. Detection of pathological voice using cepstrum vectors: A deep learning approach. Journal of Voice, 33(5), 634-641, (2019).
[32] Wang, S., Dai, Y., Shen, J.and Xuan, J. Research on expansion and classification of imbalanced data based on SMOTE algorithm. Scientific Reports, 11, 24039, (2021).
[33] Kira, K. and Rendell, L.A. A practical approach to feature selection. In Machine Learning Proceedings 1992, (pp. 249-256). Morgan Kaufmann: USA, (1992).
[34] Ghosh, P., Azam, S., Jonkman, M., Karim, A., Shamrat, F. J. M., Ignatious, E. et al. Efficient prediction of cardiovascular disease using machine learning algorithms with relief and LASSO feature selection techniques. IEEE Access, 9, 19304-19326, (2021).
[35] Vapnik, V. The Nature of Statistical Learning Theory. Springer Science & Business Media: New York, (1995).
[36] Cortes, C. Support-vector networks. Machine Learning, 20, 273-297, (1995).
[37] Chicco, D. and Jurman, G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21, 1-13, (2020).
[38] Powers, D.M. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. ArXiv Preprint, ArXiv:2010.16061, (2020).
[39] Saenz-Lechon, N., Godino-Llorente, J.I., Osma-Ruiz, V. and Gómez-Vilda, P. Methodological issues in the development of automatic systems for voice pathology detection. Biomedical Signal Processing and Control, 1(2), 120-128, (2006).
[40] Martínez, D., Lleida, E., Ortega, A., Miguel, A. and Villalba, J. Voice pathology detection on the Saarbrücken voice database with calibration and fusion of scores using multifocal toolkit. In Proceedings, Advances in Speech and Language Technologies for Iberian Languages: IberSPEECH 2012 Conference, pp. 99-109, Madrid, Spain, (2012, November).
[41] Godino-Llorente, J.I., Osma-Ruiz, V., Sáenz-Lechón, N., Cobeta-Marco, I., González-Herranz, R. and Ramírez-Calvo, C. Acoustic analysis of voice using WPCVox: a comparative study with Multi Dimensional Voice Program. European Archives of Oto-Rhino-Laryngology, 265, 465-476, (2008).
[42] Omeroglu, A.N., Mohammed, H.M. and Oral, E.A. Multi-modal voice pathology detection architecture based on deep and handcrafted feature fusion. Engineering Science and Technology, an International Journal, 36, 101148, (2022).
[43] Zhou, C., Wu, Y., Fan, Z., Zhang, X., Wu, D. and Tao, Z. Gammatone spectral latitude features extraction for pathological voice detection and classification. Applied Acoustics, 185, 108417, (2022).
[44] Lee, J.N. and Lee, J.Y. An efficient SMOTE-based deep learning model for voice pathology detection. Applied Sciences, 13(6), 3571, (2023).

Details

Primary Language

English

Subjects

Biological Mathematics, Applied Mathematics (Other)

Journal Section

Research Article

Authors

Özkan Arslan ^*
0000-0003-1949-3688
Türkiye

Publication Date

December 30, 2024

Submission Date

April 25, 2024

Acceptance Date

December 18, 2024

Published in Issue

Year 2024 Volume: 4 Number: 4

DOI

https://doi.org/10.53391/mmnsa.1473574

IZ

https://izlik.org/JA64BS86SB

APA

Arslan, Ö. (2024). A machine learning approach for voice pathology detection using mode decomposition-based acoustic cepstral features. Mathematical Modelling and Numerical Simulation With Applications, 4(4), 469-494. https://doi.org/10.53391/mmnsa.1473574

AMA

1.Arslan Ö. A machine learning approach for voice pathology detection using mode decomposition-based acoustic cepstral features. MMNSA. 2024;4(4):469-494. doi:10.53391/mmnsa.1473574

Chicago

Arslan, Özkan. 2024. “A Machine Learning Approach for Voice Pathology Detection Using Mode Decomposition-Based Acoustic Cepstral Features”. Mathematical Modelling and Numerical Simulation With Applications 4 (4): 469-94. https://doi.org/10.53391/mmnsa.1473574.

EndNote

Arslan Ö (December 1, 2024) A machine learning approach for voice pathology detection using mode decomposition-based acoustic cepstral features. Mathematical Modelling and Numerical Simulation with Applications 4 4 469–494.

IEEE

[1]Ö. Arslan, “A machine learning approach for voice pathology detection using mode decomposition-based acoustic cepstral features”, MMNSA, vol. 4, no. 4, pp. 469–494, Dec. 2024, doi: 10.53391/mmnsa.1473574.

ISNAD

Arslan, Özkan. “A Machine Learning Approach for Voice Pathology Detection Using Mode Decomposition-Based Acoustic Cepstral Features”. Mathematical Modelling and Numerical Simulation with Applications 4/4 (December 1, 2024): 469-494. https://doi.org/10.53391/mmnsa.1473574.

JAMA

1.Arslan Ö. A machine learning approach for voice pathology detection using mode decomposition-based acoustic cepstral features. MMNSA. 2024;4:469–494.

MLA

Arslan, Özkan. “A Machine Learning Approach for Voice Pathology Detection Using Mode Decomposition-Based Acoustic Cepstral Features”. Mathematical Modelling and Numerical Simulation With Applications, vol. 4, no. 4, Dec. 2024, pp. 469-94, doi:10.53391/mmnsa.1473574.

Vancouver

1.Özkan Arslan. A machine learning approach for voice pathology detection using mode decomposition-based acoustic cepstral features. MMNSA. 2024 Dec. 1;4(4):469-94. doi:10.53391/mmnsa.1473574