Voice Pathology Detection and Classification Using Convolutional Neural Network Model
Source abstract
Abstract
Voice pathology disorders can be effectively detected using computer-aided voice pathology classification tools. These tools can diagnose voice pathologies at an early stage and offering appropriate treatment. This study aims to develop a powerful feature extraction voice pathology detection tool based on Deep Learning. In this paper, a pre-trained Convolutional Neural Network (CNN) was applied to a dataset of voice pathology to maximize the classification accuracy. This study also proposes a distinguished training method combined with various training strategies in order to generalize the application of the proposed system on a wide range of problems related to voice disorders. The proposed system has tested using a voice database, namely the Saarbrücken voice database (SVD). The experimental results show the proposed CNN method for speech pathology detection achieves accuracy up to 95.41%. It also obtains 94.22% and 96.13% for F1-Score and Recall. The proposed system shows a high capability of the real-clinical application that offering a fast-automatic diagnosis and treatment solutions within 3 s to achieve the classification accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Voice and Speech Disorders · Speech Recognition and Synthesis · Music and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science and Information Technology, University of Anbar, 11, Ramadi 31001, Anbar, Iraq
College of Agriculture, Al-Muthanna University, Samawah 66001, Iraq
Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Batu Pahat 86400, Malaysia
Biomedical Computing and Engineering Technologies (BIOCORE) Applied Research Group, Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka, Durian Tunggal 76100, Malaysia
Software Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11451, Saudi Arabia
eVIDA Lab., University of Deusto, Avda/Universidades 24, 48007 Bilbao, Spain
Department of Computer Science, College of Computer and Information Systems, Umm Al-Qura University, Makkah 21421, Saudi Arabia
Faculty of Engineering, School of Electrical Engineering, Universiti Teknologi Malaysia (UTM), Johor Bahru 81310, Malaysia
References (48)
Show source-provided references
1. A Survey of Voice Pathology Surveillance Systems Based on Internet of Things and Machine Learning Algorithms10.1109/ACCESS.2020.2984925 ↗
2. Principles of Voice Production; the Journal of the Acoustical Society of America10.1121/1.424266 ↗
3. Some observations on oral air flow during phonation10.1109/TASSP.1980.1163453 ↗
4. Acoustic correlates of breathy vocal quality: Dysphonic voices and continuous speech10.1044/jshr.3902.311 ↗
5. Methodological issues in the development of automatic systems for voice pathology detection10.1016/j.bspc.2006.06.003 ↗
6. Markaki, M., and Stylianou, Y. (2009, January 3–6). Using modulation spectra for voice pathology detection and classification. Proceedings of the 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Minneapolis, MN, USA.10.1109/IEMBS.2009.5334850 ↗
7. Smart healthcare monitoring: A voice pathology detection paradigm for smart cities10.1007/s00530-017-0561-x ↗
8. Voice assessment: Updates on perceptual, acoustic, aerodynamic, and endoscopic imaging methods10.1097/MOO.0b013e3282fe96ce ↗
9. Al-Nasheri, A., Ali, Z., Muhammad, G., and Alsulaiman, M. (2014, January 10–13). Voice pathology detection using auto-correlation of different filters bank. Proceedings of the 2014 IEEE/ACS 11th International Conference on Computer Systems and Applications (AICCSA), Doha, Qatar.10.1109/AICCSA.2014.7073178 ↗
10. Voice pathology detection using interlaced derivative pattern on glottal source excitation10.1016/j.bspc.2016.08.002 ↗
11. Voice pathology detection and classification using auto-correlation and entropy features in different frequency regions
12. An incremental method combining density clustering and support vector machines for voice pathology detection10.1016/j.compeleceng.2016.08.021 ↗
13. Muhammad, G., Alhamid, M.F., Hossain, M.S., Almogren, A.S., and Vasilakos, A.V. (2017). Enhanced living by assessing voice pathology using a co-occurrence matrix. Sensors, 17.10.3390/s17020267 ↗
14. Glottal-to-noise excitation ratio–a new measure for describing pathological voices
15. Vocal fold pathology assessment using mel-frequency cepstral coefficients and linear predictive cepstral coefficients features10.1166/jmihi.2014.1253 ↗
16. An investigation of multidimensional voice program parameters in three different databases for voice pathology detection and classification10.1016/j.jvoice.2016.03.019 ↗
17. Robust and complex approach of pathological speech signal analysis10.1016/j.neucom.2015.02.085 ↗
18. Decision-level fusion scheme for nasopharyngeal carcinoma identification using machine learning techniques10.1007/s00521-018-3882-6 ↗
19. A Review of Fog Computing and Machine Learning: Concepts, Applications, Challenges, and Open Issues10.1109/ACCESS.2019.2947542 ↗
20. Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images10.1016/j.compeleceng.2018.01.033 ↗
21. Barry, J., and Püutzer, M. (2020, April 30). Saarbrucken Voice Database, Institute of Phonetics, Univ. of Saarland. Available online: http://www.stimmdatenbank.coli.uni-saarland.de/.
22. Harar, P., Alonso-Hernandezy, J.B., Mekyska, J., Galaz, Z., Burget, R., and Smekal, Z. (2017, January 10–12). Voice pathology detection using deep learning: A preliminary study. Proceedings of the 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI), Funchal, Portugal.10.1109/IWOBI.2017.7985525 ↗
23. Artificial neural networks for automatic segmentation and identification of nasopharyngeal carcinoma10.1016/j.jocs.2017.03.026 ↗
24. A real time computer aided object detection of nasopharyngeal carcinoma using genetic algorithm and artificial neural network based on Haar feature fear10.1016/j.future.2018.07.022 ↗
25. Machine learning for smart building applications: Review and taxonomy10.1145/3311950 ↗
26. Voice pathology detection using deep learning on mobile healthcare framework10.1109/ACCESS.2018.2856238 ↗
27. Examining multiple feature evaluation and classification methods for improving the diagnosis of Parkinson’s disease10.1016/j.cogsys.2018.12.004 ↗
28. Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer10.14419/ijet.v7i4.36.23737 ↗
29. Trainable model for segmenting and identifying Nasopharyngeal carcinoma10.1016/j.compeleceng.2018.07.044 ↗
30. Kukharchik, P., Martynov, D., Kheidorov, I., and Kotov, O. (2007, January 3–7). Vocal fold pathology detection using modified wavelet-like features and support vector machines. Proceedings of the 2007 15th European Signal Processing Conference, Poznan, Poland.
31. On the use of the correlation between acoustic descriptors for the normal/pathological voices discrimination10.1155/2009/173967 ↗
32. Fredouille, C., Pouchoulin, G., Bonastre, J.F., Azzarello, M., Giovanni, A., and Ghio, A. (2005, January 23). Application of automatic speaker recognition techniques to pathological voice assessment. Proceedings of the International Conference on Acoustic Speech and Signal Processing (ICASSP 2005), Philadelphia, PA, USA.10.21437/Interspeech.2005-90 ↗
33. Wang, J., and Jo, C. (Jun, 4–7). Performance of gaussian mixture models as a classifier for pathological voice. Proceedings of the 11th Australian International Conference on Speech Science and Technology, Melbourne, Australia.
34. Martínez, D., Lleida, E., Ortega, A., Miguel, A., and Villalba, J. (2012). Voice pathology detection on the Saarbrücken voice database with calibration and fusion of scores using multifocal toolkit. Advances in Speech and Language Technologies for Iberian Languages, Springer.10.1007/978-3-642-35292-8_11 ↗
35. Souissi, N., and Cherif, A. (2015, January 18–20). Dimensionality reduction for voice disorders identification system based on mel frequency cepstral coefficients and support vector machine. Proceedings of the 2015 7th International Conference on Modelling, Identification and Control (ICMIC), Sousse, Tunisia.10.1109/ICMIC.2015.7409479 ↗
36. Investigation of voice pathology detection and classification on different frequency regions using correlation functions10.1016/j.jvoice.2016.01.014 ↗
37. Voice data mining for laryngeal pathology assessment10.1016/j.compbiomed.2015.07.026 ↗
38. Voice Pathologies Classification and Detection Using EMD-DWT Analysis Based on Higher Order Statistic Features10.1016/j.irbm.2019.11.004 ↗
39. Acoustic investigation of speech pathologies based on the discriminative paraconsistent machine (DPM)10.1016/j.bspc.2019.101615 ↗
40. Rueda, A., and Krishnan, S. (2019, January 12–17). Augmenting Dysphonia Voice Using Fourier-based Synchrosqueezing Transform for a CNN Classifier. Proceedings of the ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8682391 ↗
41. Pouchoulin, G., Fredouille, C., Bonastre, J.F., Ghio, A., and Révis, J. (2007). Characterization of the Pathological Voices (Dysphonia) in the Frequency Space, International Congress of Phonetic Sciences (ICPhS).
42. Characterization of dysphonic voices by means of a filterbank-based spectral analysis: Sustained vowels and running speech10.1016/j.jvoice.2012.07.004 ↗
43. K-means clustering and neural network for object detecting and identifying abnormality of brain tumor10.1007/s00500-018-3618-7 ↗
44. Little, M., McSharry, P., Hunter, E., and Ramig, L. (2008). Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease. Nat. Prec.10.1038/npre.2008.2298.1 ↗
45. A survey on transfer learning10.1109/TKDE.2009.191 ↗
46. Ishaq, R., Zapirain, B.G., Shahid, M., and Lovstrom, B. (2013, January 26–31). Subband Modulator Kalman filtering for Single Channel Speech Enhancement. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada.10.1109/ICASSP.2013.6639109 ↗
47. Garcia, B., Vicente, J., Alonso, A., and Loyo, E. (2005, January 23). Esophageal voices: Glottal flow restoration. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Philadelphia, PA, USA.
48. Garcia, B., Ruiz, I., Vicente, J., and Alonso, A. (2006, January 27–30). Formants measurement for esophageal speech using wavelet with band and resoultion adjustment. Proceedings of the 2006 IEEE International Symposium on Signal Processing and Information Technology, Vancouver, BC, Canada.10.1109/ISSPIT.2006.270819 ↗