Voice disorders are abnormal characteristic of sound produced by larynx involving pitch, intensity, loudness. Nowadays Voice disorders are one among rapidly spreading diseases. Disordered quality of voice could also be a symptom for laryngeal diseases. The goal of this work is to build a model to identify the types of voice disorders that includes Normal, Dysphonia, Stammering and Vocal palsy. To deal with this classification problem, Machine learning classifier Support Vector Machine (SVM) is used. The results are evaluated in terms of accuracy, sensitivity, specificity and ROC based on the features extracted using Mel Frequency Cepstral Coefficients (MFCCs), they are the cepstral representation of audio clip.

Voice disorders, Machine Learning, Classification, SVM, MFCC

[1] N. Souissi and A. Cherif, “Dimensionality reduction for voice disorders identification system based on mel frequency cepstral coefficients”, In the Proceedings of the 2015 7th International Conference on Modelling, Identification and Control, pp. 1-6, 2015.
[2] Byron D. Erath, Matias Zanartu, Kelly C. Stewart, Michael W. Plesniak, David E. Sommer, Sean D. Peterson, “A review of lumped-element models of voiced speech”, Speech Communication Publisher, US, pp. 667-690, 2013.
[3] Arias-Londoño JD, Godino-Llorente JI, Markaki M, Stylianou Y, “On combining information from modulation spectra and mel-frequency cepstral coefficients for automatic detection of pathological voices”, Logoped Phoniatr Vocol, 2011 Jul, pp. 36(2):60-9.
[4] Edwin L, Kendig, Robert W. Wilmott, Victor Chernick, “Disorders of the Respiratory Tract in Children”, Elsevier Health Sciences Publisher, 2012.
[5] K. Hajian-Tilaki, “Receiver operating characteristic (roc) curve analysis for medical diagnostic test evaluation”, Caspian journal of internal medicine, vol. 4, no. 2, p. 627, 2013.
[6] S. C. Costa, B. G. Aguiar Neto and J. M. Fechine, "Pathological voice discrimination using cepstral analysis, vector quantization and Hidden Markov Models", 2008 8th IEEE International Conference on BioInformatics and BioEngineering, Athens, 2008, pp. 1-5.
[7] Fathima Kunhi Mohamed, Lajish V.L, et al. “Nonlinear Speech Analysis and Modeling for Vowel Recognition”, 6th International Conference On Advances In Computing & Communications, 2016, Cochin, India.
[8] Galindo, Gabriel E, et al, “Modeling the pathophysiology of phonotraumatic vocal hyperfunction with a triangular glottal model of the vocal folds”. Journal of Speech, Language, and Hearing Research, Vol. 60 2452–2471, 2017
[9] J. I. Godino-Llorente, P. Gomez-Vilda and M. Blanco-Velasco, "Dimensionality Reduction of a Pathological Voice Quality Assessment System Based on Gaussian Mixture Models and Short-Term Cepstral Parameters", in IEEE Transactions on Biomedical Engineering, vol. 53, no. 10, pp. 1943-1953, 2006.
[10] Wu, Huiyi, et al. "A deep learning method for pathological voice detection using convolutional deep belief networks", Interspeech 2018.
[11] K. Umapathy, S. Krishnan, V. Parsa and D. G. Jamieson, "Discrimination of pathological voices using a time-frequency approach", in IEEE Transactions on Biomedical Engineering, vol. 52, no. 3, pp. 421-430, March 2005.
[12] T. Marciniak, R. Weychan, S. Drgas, A. Dabrowski, and A. Krzykowska, “Speaker recognition based on short polish sequences”, in Signal Processing Algorithms, Architectures, Arrangements, and Applications Conference Proceedings (SPA), 2010. IEEE, 2010, pp. 95–98.
[13] M. S. Hossain, “Patient state recognition system for healthcare using speech and facial expressions”, Journal of medical systems, vol. 40, no. 12, p. 272, 2016.
[14] International Journal of Scientific Research in Network Security and Communication (ISSN: 2321-3256).
[15] Gourish Malage, Kiran Kumari Patil, “A Voice based Farmer Information System”, International Journal of Scientific Research in Computer Sciences and Engineering, Vol.7, Issue.6, pp.220-224,2019.
[16] Sujitha Perumal, Mohammed Saqib Javid, “Voice Enabled Smart Home Assistant for Elderly”, International Journal of Scientific Research in Computer Sciences and Engineering, Vol.7, Issue.11, pp. 30-37, 2019.
[17] M. Mat Baki, G. Wood, M. Alston, P. Ratcliffe, G. Sandhu, J. Rubin, and M. Birchall, “Reliability of operavox against multidimensional voice program (mdvp)”, Clinical Otolaryngology, vol. 40, no. 1, pp. 22–28, 2015.