Automatic voice pathology detection enables an objective assessment of pathologies that influence the voice production strategy. By utilizing the conventional pipeline model as well as the modern deep learning-centric end-to-end methodology, numerous pathological voice analyzing techniques have been developed. The conventional methodology is still a valid choice owing to the lack of enormous amounts of training data in the study region of pathological voice. In the meantime, obtaining higher precision, higher accuracy, and stability is still a complicated task. Therefore, by amalgamating the nonlinear measure, the pathological voices are analyzed to abate such risks. The viability of six nonlinear discriminating measures derived from the phase space realm, involving healthy and pathological voice signals, is studied in this work. The analyzed parameters are Singularity spectrum coefficients ( $α_{min}$ , $α_{max}, γ_{1}$ and $γ_{2}$ ). Correlation entropy at optimum embedding dimension ( $K_{2 m}$ ) and correlation dimension at optimum embedding dimension ( $D_{2 m}$ ). Analyzing the pathological voices with better accuracy rates is the major objective of the proposed methodology. Here, the Support Vector Machine (SVM) was utilized as the classifier. Experimentations were performed on VOiceICarfEDerico (VOICED) databases subsuming 208 healthy, as well as pathological voices, amongst these 50 samples, were utilized. Here, the model obtained 97% of accuracy with 99% as of the classifier with Gaussian kernel function. Therefore, to differentiate normal as well as pathological subjects, the six proposed characteristics are highly beneficial; in addition, they will be supportive in pathology diagnosis.

Keywords:

Remember to check out the Check out our Most Cited Articles!
Check out these titles on Image Analysis

References

1. G. Vaziri, F. Almasganj and R. Behroozmand , “Pathological assessment of patients’ speech signals using nonlinear dynamical analysis,” Comput. Biol. Med. 40(1), 54–63 (2010), https://doi.org/10.1016/j.compbiomed.2009.10.011. Crossref, Google Scholar
2. P. Henríquez, J. B. Alonso, M. A. Ferrer, C. M. Travieso, J. I. Godino-Llorente and F. Díaz-de-María , “Characterization of healthy and pathological voice through measures based on nonlinear dynamics,” IEEE Trans. Audio Speech Lang. Process. 17(6), 1186–1195 (2009), https://doi.org/10.1109/TASL.2009.2016734. Crossref, Google Scholar
3. B. Boyanov, S. Hadjitodorov, B. Teston and D. Doskov , “Robust hybrid pitch detector for pathological voice analysis,” in Larynx’97, France, Int. Speech Communication Association (1997), pp. 55–58. Available at: http://www.isca-speech.org/archive_open/larynx_97/lar7_055.html. Google Scholar
4. R. J. T. De Sousa , “A new accurate method of harmonic-to-noise ratio extraction,” in Proc. Int. Conf. Bio-inspired Systems and Signal Processing (2011), pp. 351–356, https://doi.org/10.5220/0001552903510356. Google Scholar
5. Y. Qi and R. E. Hillman , “Temporal and spectral estimations of harmonics-to-noise ratio in human voice signals,” J. Acoust. Soc. Am. 102(1), 537–543 (1997), https://doi.org/10.1121/1.419726. Crossref, Google Scholar
6. L. Gu and J. G. Harris , “Disordered speech assessment using automatic methods based on quantitative measures,” EURASIP J. Appl. Signal Process. 9(1), 1400–1409 (2005), https://doi.org/10.1155/ASP.2005.1400. Google Scholar
7. B. Boyanov and S. Hadjitodorov , “Acoustic analysis of pathological voices: A voice analysis system for the screening and laryngeal diseases,” IEEE Eng. Med. Biol. Mag. 16(4), 74–82 (1997), https://doi.org/10.1109/51.603651. Crossref, Google Scholar
8. E. J. Wallen and J. H. L. Hansen , “A screening test for speech pathology assessment using objective quality measures,” in Proc. 4th Int. Conf. Spoken Language Processing, Vol. 2 (IEEE, 1996), pp. 776–779, https://doi.org/10.1109/CSLP.96.607478. Google Scholar
9. S. Hadjitodorov and P. Mitev , “A computer system for acoustic analysis of pathological voices and laryngeal diseases screening,” Med. Eng. Phys. 24(6), 419–429 (2002), https://doi.org/10.1016/S1350-4533(02)00031-0. Crossref, Google Scholar
10. S. R. Kadiri and P. Alku , “Analysis and detection of pathological voice using glottal source features,” IEEE J. Sel. Top. Signal Process. 14(2), 367–379 (2020), https://doi.org/10.1109/JSTSP.2019.2957988. Crossref, Google Scholar
11. E. Bradley and H. Kantz , “Nonlinear time-series analysis revisited,” Chaos 25(9), 097610 (2015), https://doi.org/10.1063/1.4917289. Crossref, Google Scholar
12. V. Pitsikalis and P. Maragos , “Analysis and classification of speech signals by generalized fractal dimension features,” Speech Commun. 51(12), 1206–1223 (2009), https://doi.org/10.1016/j.specom.2009.06.005. Crossref, Web of Science, Google Scholar
13. C. Fang, H. Li, L. Ma and X. Zhang , “Nonlinear dynamic analysis of pathological voices,” in Int. Conf. Intelligent Computing, Vol. 7996 (Springer, Berlin, Heidelberg, 2013), pp. 401–409, https://doi.org/10.1007/978-3-642-39482-9_46. Google Scholar
14. R. Palaniappan , “Reliable system for respiratory pathology classification from breath sound signals,” in 2016 Int. Conf. System Reliability and Science (IEEE, 2016), pp. 152–156. Crossref, Google Scholar
15. D. Panek, A. Skalski and J. Gajda , “Quantification of linear and non-linear acoustic analysis applied to voice pathology detection,” in Information Technologies in Biomedicine, Vol. 4 (Springer, Cham, 2014), pp. 355–364, https://doi.org/10.1007/978-3-319-06596-0_33. Google Scholar
16. N. Huang, Y. Zhang, W. Calawerts and J. J. Jiang , “Optimized nonlinear dynamic analysis of pathologic voices with laryngeal paralysis based on the minimum embedding dimension,” J. Voice 31(2), 249.e1–249.e7 (2017), https://doi.org/10.1016/j.jvoice.2016.07.021. Crossref, Web of Science, Google Scholar
17. U. Cesari, G. De Pietro, E. Marciano, C. Niri, G. Sannino and L. Verde , “A new database of healthy and pathological voices,” Comput. Electr. Eng. 68, 310–321 (2018), https://doi.org/10.1016/j.compeleceng.2018.04.008. Crossref, Web of Science, Google Scholar
18. R. Hegger, H. Kantz and T. Schreiber , “Practical implementation of nonlinear time series methods: The TISEAN package,” Chaos 9(2), 413–435 (1999), https://doi.org/10.1063/1.166424. Crossref, Web of Science, Google Scholar
19. K. P. Harikrishnan, R. Misra, G. Ambika and R. E. Amritkar , “Computing the multifractal spectrum from time series: An algorithmic approach,” Chaos 19, 043129 (2009), https://doi.org/10.1063/1.3273187. Crossref, Web of Science, Google Scholar
20. K. P. Harikrishnan, G. Ambika and R. Misra , “An algorithmic computation of correlation dimension from time series,” Mod. Phys. Lett. B 21, 129–138 (2007). Link, Web of Science, Google Scholar
21. K. P. Harikrishnan, R. Misra and G. Ambika , “Efficient use of correlation entropy for analysing time series data,” Pramana-J. Phys. 72(2), 325–326 (2009). Crossref, Web of Science, Google Scholar
22. P. Grassberger and I. Procaccia , “Characterization of strange attractors,” Phys. Rev. Lett. 50(5), 346–349 (1983), https://doi.org/10.1103/PhysRevLett.50.346. Crossref, Web of Science, Google Scholar
23. M. A. Hong-guang and H. A. N. Chong-zhao , “Selection of embedding dimension and delay time in phase space reconstruction,” Front. Electr. Electron. Eng. China 1, 111–114 (2006), https://doi.org/10.1007/s11460-005-0023-7. Crossref, Google Scholar
24. J. A. A. Filho, A. C. P. L. F. Carvalho, R. F. Mello, S. Alelyani and H. Liu , “Quantifying features using false nearest neighbors: An unsupervised approach,” in Proc. - Int. Conf. Tools with Artificial Intelligence (IEEE, 2011), pp. 994–997, https://doi.org/10.1109/ICTAI.2011.170. Crossref, Google Scholar
25. A. Stefanovska , “Surrogate data for hypothesis testing of physical systems,” Phys. Rep. 748, 1–60 (2018), https://doi.org/10.1016/j.physrep.2018.06.001. Crossref, Web of Science, Google Scholar
26. A. C. G. Thome , “SVM classifiers – Concepts and applications to character recognition,” in Advances in Character Recognition (2012), pp. 25–49. Available at: http://www.intechopen.com/books/advances-in-character-recognition. Crossref, Google Scholar
27. B. A. Sonkamble and D. D. Doye , “An overview of speech recognition system based on the support vector machines,” in Proc. Int. Conf. Computer and Communication Engineering 2008 (IEEE, 2008), pp. 768–771, https://doi.org/10.1109/ICCCE.2008.4580709. Crossref, Google Scholar
28. X.-J. Zhang, X.-C. Zhu, D. Wu, Z.-Z. Xiao, Z. Tao and H.-M. Zhao , “Nonlinear features of bark wavelet sub-band filtering for pathological voice recognition,” Eng. Lett. 29(1), 1–12 (2021). Web of Science, Google Scholar
29. T. Zhang, X. Liu, G. Liu and Y. Shao , “PVR-AFM: A pathological voice repair system based on non-linear structure,” J. Voice, 1–15 (2021), https://doi.org/10.1016/j.jvoice.2021.05.010. Google Scholar
30. X. Zhang, X. Zhu, C. Zhou, Z. Tao and H. Zhao , “Pathological voice classification based on the features of an asymmetric fluid-structure interaction vocal cord model,” Appl. Acoust., 1–25 (2022), Available at: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4259094. Google Scholar
31. M. K. Reddy and P. Alkua , “Comparison of cepstral features in the detection of pathological voices by varying the input and filterbank of the cepstrum computation,” IEEE Access 9, 135953–135963 (2021). Crossref, Web of Science, Google Scholar
32. H. Ding, Z. Gu, P. Dai, Z. Zhou, L. Wang and X. Wu , “Deep connected attention (DCA) ResNet for robust voice pathology detection and classification,” Biomed. Signal Process. Control 70, 1–9 (2021). Crossref, Web of Science, Google Scholar