Machine Learning Approach to Dysphonia Detection
Source abstract
Abstract
This paper addresses the processing of speech data and their utilization in a decision support system. The main aim of this work is to utilize machine learning methods to recognize pathological speech, particularly dysphonia. We extracted 1560 speech features and used these to train the classification model. As classifiers, three state-of-the-art methods were used: K-nearest neighbors, random forests, and support vector machine. We analyzed the performance of classifiers with and without gender taken into account. The experimental results showed that it is possible to recognize pathological speech with as high as a 91.3% classification accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Voice and Speech Disorders · Speech Recognition and Synthesis · Phonetics and Phonology Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computers and Informatics, Faculty of Electrical Engineering and Informatics, Technical University of Košice, 040 01 Košice, Slovakia
References (29)
Show source-provided references
1. Lopez-de-Ipina, K., Satue-Villar, A., Faundez-Zanuy, M., Arreola, V., Ortega, O., Clave, P., Sanz-Cartagena, M., Mekyska, J., and Calvo, P. (2016). Advances in a Multimodal Approach for Dysphagia Analysis Based on Automatic Voice Analysis. Advances in Neural Networks, Springer International Publishing.10.1007/978-3-319-33747-0_20 ↗
2. Hirano, M. (1981). Psycho-Acoustic Evaluation of Voice, Springer.
3. Baken, R.J., and Orlikoff, R.F. (2000). Clinical Measurement of Speech and Voice, Singular Thomson Learning.
4. Robust and complex approach of pathological speech signal analysis10.1016/j.neucom.2015.02.085 ↗
5. Understanding technology adoption in clinical care: Clinician adoption behavior of a point-of-care reminder system10.1016/j.ijmedinf.2005.03.007 ↗
6. Clinical decision support systems for the practice of evidence-based medicine10.1136/jamia.2001.0080527 ↗
7. A two-stage variable selection and classification approach for Parkinson’s disease detection by using voice recording replications10.1016/j.cmpb.2017.02.019 ↗
8. Automatic voice analysis for dysphagia detection10.1080/2050571X.2017.1369017 ↗
9. Gupta, R., Chaspari, T., Kim, J., Kumar, N., Bone, D., and Narayanan, S. (2016, January 20–25). Pathological speech processing: State-of-the-art, current challenges, and future directions. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.10.1109/ICASSP.2016.7472923 ↗
10. Advanced Information Technology-support of improved personalized therapy of speech disorders10.15837/ijccc.2010.5.2224 ↗
11. Voice Pathology Detection and Classification using Auto-correlation and entropy features in Different Frequency Regions
12. Martinez, D. (2012). Voice Pathology Detection on the Saarbrücken Voice Database with Calibration and Fusion of Scores Using MultiFocal Toolkit. Communications in Computer and Information Science, Springer.10.1007/978-3-642-35292-8_11 ↗
13. Suitability of Dysphonia Measurements for Telemonitoring of Parkinson’s Disease10.1109/TBME.2008.2005954 ↗
14. Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson’s disease symptom severity10.1098/rsif.2010.0456 ↗
15. Saldert, C., and Bauer, M. (2017). Multifaceted Communication Problems in Everyday Conversations Involving People with Parkinson’s Disease. Brain Sci., 7.10.3390/brainsci7100123 ↗
16. Advances on Automatic Speech Analysis for Early Detection of Alzheimer Disease: A Non-linear Multi-task Approach10.2174/1567205014666171120143800 ↗
17. Self-Organizing Maps For Identifying Impaired Speech10.4316/aece.2011.03007 ↗
18. Use of machine learning to improve autism screening and diagnostic instruments: Effectiveness, efficiency, and multi-instrument fusion10.1111/jcpp.12559 ↗
19. Bone, D., Gibson, J., Chaspari, T., Can, D., and Narayanan, S. (2016, January 6–9). Speech and language processing for mental health research and care. Proceedings of the 2016 50th Conference on Signals, Systems and Computers, Pacific Grove, CA, USA.10.1109/ACSSC.2016.7869164 ↗
20. Barry, B. (2017, February 23). Saarbruecken Voice Database. Available online: http://stimmdb.coli.uni-saarland.de/.
21. Feature selection in machine learning: A new perspective10.1016/j.neucom.2017.11.077 ↗
22. Comparative study of machine learning techniques for supervised classification of biomedical data10.15546/aeei-2014-0021 ↗
23. Least squares support vector machine classifiers10.1023/A:1018628609742 ↗
24. Vapnik, V. (1998). Statistical Learning Theory, Willey-Interscience.
25. Akbulut, Y., Sengur, A., Guo, Y., and Smarandache, F. (2017). NS-k-NN: Neutrosophic Set-Based k-Nearest Neighbors Classifier. Symmetry, 9.10.3390/sym9090179 ↗
26. A random forest approach using imprecise probabilities10.1016/j.knosys.2017.07.019 ↗
27. Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics10.1002/widm.1072 ↗
28. Raschka, S. (2015). Python Machine Learning, Packt Publishing Ltd.
29. Analysis of alcoholic EEG signals based on horizontal visibility graph entropy10.1007/s40708-014-0003-x ↗