Detection of Voice Pathologies with Information Theory Based Features

Abstract

Voice is produced by excited dynamic vocal tract system consisting of vocal cords, lips, tongue, with the air from lungs. Pathological cases in these components change the characteristics of the voice. Voice diseases impair quality of life, and some pathologies can be life-threatening, so early diagnosis is important. In literature, voice disorders can be generally investigated with traditional or acoustics signal analysis methods and detected by using machine learning. In this study, analysis and classification studies were realized for detecting vocal cord deformities such as cyst, polyp and sulcus vocalis, and healthy ones. Unlike literature, instead of acoustic features, features based on information theory such as recurrence plot quantities, entropies and dimensions coming from nonlinear approaches were used. Three feature selection and three classification methods were tried with nonlinear features calculated from whole signal and decomposed signal with discrete wavelet transform. Two classification procedures (binary and multiple class) with 10-fold cross validation were applied and tested with distinct groups. According to the results, in binary classification (healthy/ diseased), the best test accuracy of 99.2% with Coarse Tree classifier was obtained with only four features selected with MRMR algorithm. In multiclass (healthy/cyst/polyp/sulcus), the test accuracy of 91.6% was found as the best with only eight selected features by using ANOVA and Kernel Naive Bayes classifier. The results show that the use of a few features coming from nonlinear domain provided very effective and successful in classifying voice disorders in both binary and multiclass when compared to the studies in the literature.

Keywords

• Vocal cord diseases
• Recurrence plots quantities
• Discrete wavelet transform
• Feature selection
• Binary and multiclass classification

References

1. [1] Bhattacharyya, N., “The prevalence of voice problems among adults in the United States”, The Laryngoscope, 124: 2359-2362, (2014). DOI: https://doi.org/10.1002/lary.24740
2. [2] Hossain, M. S., Muhammad, G., Alamri, A., “Smart healthcare monitoring: A voice pathology detection paradigm for smart cities”, Multimedia Systems, 25: 565-575, (2017). DOI: https://doi.org/10.1007/s00530-017-0561-x
3. [3] Kılıç M., “Ses problemi olan hastanın objektif ve subjektif yöntemlerle değerlendirilmesi”, Kulak Burun Boğaz Baş Boyun Cerrahisi’nde Güncel Yaklaşım, 6, (2010).
4. [4] Hegde, S., Shetty, S., Rai, S., Dodderi, T., “A survey on machine learning approaches for automatic detection of voice disorders”, Journal of Voice, 33(6): 947.e11-947.e33, (2019). DOI: https://doi.org/10.1016/j.jvoice.2018.07.014
5. [5] Mohamed, A. N., Salama, A. A., Darwish, S. H., “Classification of voice pathology using SVM classifier”, International Telecommunications Conference (ITC-Egypt), Alexandria, Egypt, 419-422, (2023). DOI: https://doi.org/10.1109/ITC-Mısır58155.2023.10206116
6. [6] Gayathri, S., Priya, E., “Identification of voice pathology from temporal and cepstral features for vowel ‘a’ low intonation”, International Conference on Electronic Systems and Intelligent Computing (ICESIC), Chennai, India, 345-350, (2022). DOI: https://doi.org/10.1109/ICESIC53714.2022.9783484
7. [7] Murthy, G. L. N., Iswarya, V., Ramya Sri, K., Harshitha, K., Prasanth, Ch., “A novel algorithm for detecting spasmodic dysphonia voice pathology using random forest framework”, International Conference on Edge Computing and Applications (ICECAA), Tamilnadu, India, 800-804, (2022). DOI: https://doi.org/10.1109/ICECAA55415.2022.9936567
8. [8] Miliaresi, I., Poutos, K., Pikrakis, A., “Combining acoustic features and medical data in deep learning networks for voice pathology classification”, 28th European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands, 1190-1194, (2021). DOI: https://doi.org/10.23919/Eusipco47968.2020.9287333

9. [9] Ribas, D., Pastor, M. A., Miguel, A., Martinez, D., Ortega, A., Lleida, E., “Automatic voice disorder detection using self-supervised representations”, IEEE Access, 11: 14915-14927, (2023). DOI: https://doi.org/10.1109/ACCESS.2023.3243986
10. [10] Barche, P., Gurugubelli, K., Vuppala, A. K., “Comparative study of different epoch extraction methods for speech associated with voice disorders”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, 6923-6927, (2021). DOI: https://doi.org/10.1109/ICASSP39728.2021.9413518
11. [11] AnilKumar, V., Venkata Siva Reddy, R., “Classification of voice pathology using different features and Bi-LSTM”, 2023 International Conference on Smart Systems for applications in Electrical Sciences (ICSSES), Tumakuru, India, 1-4, (2023). DOI: https://doi.org/10.1109/ICSSES58299.2023.10200529
12. [12] Ali, Z., Herrera, A. G. S., Mesallam, T. A., Muhammad, G., “Computer-based blind diagnostic system for classification of healthy and disordered voices”, IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS), L'Aquila, Italy, 654-659, (2023). DOI: https://doi.org/10.1109/CBMS58004.2023.00295
13. [13] Wang C. T., Chuang Z. Y., Hung C. H., Tsao Y., Fang S. H., “Detection of glottic neoplasm based on voice signals using deep neural networks”, IEEE Sensors Letters, 6(3): 1-4, (2022). DOI: https://doi.org/10.1109/LSENS.2022.3152738
14. [14] Suresh M., Rajan R., Thomas J., “Dysarthria speech disorder classification using traditional and deep learning models”, Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), Trichirappalli, India, 01-06, (2023). DOI: https://doi.org/10.1109/ICEEICT56924.2023.10157285
15. [15] Sahane, P., Pangaonkar S., Khandekar S., “Dysarthric speech recognition using multi-taper Mel frequency cepstrum coefficients”, International Conference on Computing, Communication and Green Engineering (CCGE), Pune, India, 1-4, (2021). DOI: https://doi.org/10.1109/CCGE50943.2021.9776318
16. [16] Rebecca, M. G., Anjana, A., Arthi, V., Dhanalakshmi, M., Babu, R. D., “Machine learning based vowel analysis in severity level detection of voice pathology”, 6th International Conference on Electronics, Communication and Aerospace Technology, Coimbatore, India, 1005-1008, (2022). DOI: https://doi.org/10.1109/ICECA55336.2022.10009604
17. [17] Vieira V. J. D., Costa S. C., Correia S. E. N., “Non-stationarity-based adaptive segmentation applied to voice disorder discrimination”, IEEE Access, 11: 54750-54759, (2023). DOI: https://doi.org/10.1109/ACCESS.2023.3281191
18. [18] Islam R., Tarique M., “Robust assessment of dysarthrophonic voice with RASTA-PLP features: A nonlinear spectral measures”, 2nd International Conference on Mechatronics and Electrical Engineering (MEEE), Abu Dhabi, United Arab Emirates, 74-78, (2023). DOI: https://doi.org/10.1109/MEEE57080.2023.10126695
19. [19] Ankışhan H., İnam S. Ç., “Voice pathology detection by using the deep network architecture”, Applied Soft Computing, 106, (2021). DOI: https://doi.org/10.1016/j.asoc.2021.107310
20. [20] Mallat, S.G., “A theory for multiresolution signal decomposition: The wavelet representation”, IEEE.Transactions on Pattern Analysis and Machine Intelligence, 11: 674-693, (1989). DOI: https://doi.org/10.1109/34.192463
21. [21] Mihoc, S. G., Popov, A. N., Ivanov, R., “Denoising speech signals by wavelet transform”, Annual Journal of Electronics, (2009).
22. [22] Dautov, Ç. P., Özerdem, M. S., “Wavelet transform and signal denoising using wavelet method”, 26th Signal Processing and Communications Applications Conference (SIU), (2018). DOI: https://doi.org/10.1109/SIU.2018.8404418
23. [23] Daubechies, I., “Orthonormal bases of compactly supported wavelets”, Communications on Pure and Applied Math., 41: 909-996, (1988). DOI: https://doi.org/10.1002/cpa.3160410705
24. [24] Shannon, C. E., “Mathematical theory of communication”. Bell Syst. Tech. J., 27: 379-423, 623–656, (1948). DOI: https://doi.org/10.1002/j.1538-7305.1948.tb01338.x
25. [25] Lau, Y.K., Chan, C.-K., “Speech recognition based on zero crossing rate and energy,” IEEE Transactions on Acoustics, Speech, and Signal Processing, 33(1): 320-3233, (1985). DOI: https://doi.org/10.1109/TASSP.1985.1164503
26. [26] Misra, H., Ikbal, S., Bourlard, H., Hermansky, H., “Spectral Entropy Based Feature for Robust ASR”, IEEE International Conference on Acoustics, Speech, and Signal Processing, (2004). DOI: https://doi.org/10.1109/ICASSP.2004.1325955
27. [27] Higuchi, T., “Approach to an irregular time series on the basis of the fractal theory”, Physica D, 31: 277-283, (1988). DOI: https://doi.org/10.1016/0167-2789(88)90081-4
28. [28] Katz, M. J., “Fractals and the analysis of waveforms,” Computers in Biology and Medicine, 18(3): 145-56, (1988). DOI: https://doi.org/10.1016/0010-4825(88)90041-8
29. [29] Norbert Marwan, M., Romano, C., Thiel, M., Kurths, J., “Recurrence plots for the analysis of complex systems”, Physics Reports, 438: 237-329, (2007). DOI: https://doi.org/10.1016/j.physrep.2006.11.001
30. [30] Robnik-Sikonja, M., Kononenko. I., “Theoretical and empirical analysis of ReliefF and RReliefF”, Machine Learning, 53: 23-69, (2003). DOI: https://doi.org/10.1023/A:1025667309714
31. [31] Hogg, R. V., Ledolter. J., “Engineering Statistics”, New York: MacMillan, (1987).
32. [32] Darbellay, G. A., Vajda, I., “Estimation of the information by an adaptive partitioning of the observation space”, IEEE Transactions on Information Theory, 45(4): 1315-1321, (1999). DOI: https://doi.org/10.1109/18.761290
33. [33] Quinlan, J. R., “Induction of decision trees”, Machine Learning, 1: 81-106, (1986). DOI: https://doi.org/10.1007/BF00116251
34. [34] Manning, C. D., P. Raghavan, M. Schütze, “Introduction to Information Retrieval”, NY: Cambridge University Press, (2008). DOI: https://doi.org/10.1017/CBO9780511809071
35. [35] Polikar, R., “Ensemble based systems in decision making”, IEEE Circuits and systems magazine, 6(3): 21-45, (2006). DOI: https://doi.org/10.1109/MCAS.2006.1688199
36. [36] Atilkan, Y., Kirik, B., Acici, K., Benzer, R., Ekinci, F., Guzel, M.S., Benzer, S., Asuroglu, T., “Advancing crayfish diseased detection: A comparative study of deep learning and canonical machine learning techniques”, Applied Sciences, 14, 6211, (2024). DOI: https://doi.org/10.3390/app14146211
37. [37] Tombaloğlu, B., Erdem, H., “Turkish speech recognition techniques and applications of recurrent units (LSTM and GRU)”, Gazi University Journal of Science, 34(4): 1035-1049, (2021). DOI: https://doi.org/10.35378/gujs.816499
38. [38] Disken, G., “Robust spoofed speech detection with denoised I-vectors”, Gazi University Journal of Science, 36(4): 1553-1561, (2023). DOI: https://doi.org/10.35378/gujs.1062788