Identification of Laryngeal Disorders Based On MFCC and Jitter and Shimmer Features and PSO Classifier

Laryngeal disorders are very uncomfortable and unbearable due to the continuous use of the human voice. However,the better identification of laryngeal disorders always is necessary. Recently, a lot of researchers such as doctors and biomedical engineers directed to the non-invasive and easier methods to detect disorders. The advantage of this method compared with invasive methods, are its tolerable for the patient and its more speed in achieve to the final result. Including new and non-invasive methods to diagnose of laryngeal disorders are audio signal processing method, which due to the effect that anomaly puts on the human voice; its type will be detected. Most of the researches that has been done so far are separated patients and healthy persons from each other and a few of studies have done classification of several disorders from between various disorders. In the proposed work, Feature extraction is done in three ways, the first depending on MFCC features and the second depending on Jitter and Shimmer features and the third by combining MFCC and Jitter and Shimmer. Meanwhile, achieved features are used along with PSO algorithm to analyse and classify anomalies based on several classes. Also, we used four groups of anomalies and a class of normal voice as benchmark data sets and evaluated and compared the proposed method with different feature extraction strategy. Our simulations results confirm the superior performance of the proposed method, especially when the features are extracted based on combination of MFCC and Jitter Shimmer. The result from the combination is 80% and using MFCC alone is 66% and using Shimmer and Jitter is 43%.