International Journal of Electrical and Computer Engineering (IJECE) Vol. 12, No. 1, February 2022, pp. 946~956 ISSN: 2088-8708, DOI: 10.11591/ijece.v12i1.pp946-956  946 Journal homepage: http://ijece.iaescore.com Classification of three pathological voices based on specific features groups using support vector machine Muneera Altayeb 1 , Amani Al-Ghraibah 2 1 Department of Electronics and Communications Engineering, Faculty of Engineering, Al-Ahliyya Amman University, Amman, Jordan 2 Department of Medical Engineering, Faculty of Engineering, Al-Ahliyya Amman University, Amman, Jordan Article Info ABSTRACT Article history: Received Feb 10, 2021 Revised Aug 3, 2021 Accepted Aug 20, 2021 Determining and classifying pathological human sounds are still an interesting area of research in the field of speech processing. This paper explores different methods of voice features extraction, namely: Mel frequency cepstral coefficients (MFCCs), zero-crossing rate (ZCR) and discrete wavelet transform (DWT). A comparison is made between these methods in order to identify their ability in classifying any input sound as a normal or pathological voices using support vector machine (SVM). Firstly, the voice signal is processed and filtered, then vocal features are extracted using the proposed methods and finally six groups of features are used to classify the voice data as healthy, hyperkinetic dysphonia, hypokinetic dysphonia, or reflux laryngitis using separate classification processes. The classification results reach 100% accuracy using the MFCC and kurtosis feature group. While the other classification accuracies range between~60% to~97%. The Wavelet features provide very good classification results in comparison with other common voice features like MFCC and ZCR features. This paper aims to improve the diagnosis of voice disorders without the need for surgical interventions and endoscopic procedures which consumes time and burden the patients. Also, the comparison between the proposed feature extraction methods offers a good reference for further researches in the voice classification area. Keywords: Discrete wavelet transform Mel frequency cepstral- coefficients Support vector machine Voice disorders This is an open access article under the CC BY-SA license. Corresponding Author: Muneera Altayeb Department of Electronics and Communications Engineering, Faculty of Engineering, Al-Ahliyya Amman University Al-Saro, Al-Salt, Amman, Jordan Email: m.altayeb@ammanu.edu.jo 1. INTRODUCTION Speech is considered as one of the most important means of communication among humans. Therefore, when any defect occurs in the speech system, this considered as an impediment in communication among people. Difficulty in speech may arise due to imbalance in the speech or auditory system [1]. Many researchers in literature have studied speech disorders and vocal pathology by analyzing and classifying samples of patient’s voices. The purpose was to help patients with pathological problems and to monitor the progress of the vocal therapy pathway and to minimize the use of traditional diagnostic pathologies of vocal pathology. Researchers developed many diagnosis methods for observations of vocal folds by means of laparoscopic tools. However, these techniques are risky, time consuming, discomfort and require expensive resources [2], [3]. From the in Ankışhan work [4], a new approach for detection of pathological voice disorders was developed with minimum parameters. The preprocessing step has been carried out since the recording of the sound data. The sound data is re-modeled with the calculated