Voice pathology analysis has been one of the useful tools in the diagnosis of the pathological voice, as the method is non-invasive, inexpensive, and can reduce the time required for the analysis. This paper investigates feature extraction based on the Dual-Tree Complex Wavelet Packet Transform (DT-CWPT) using energy and entropy measures tested with two classifiers, k-Nearest Neighbors (k-NN) and Support Vector Machine (SVM). Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database and Saarbruecken Voice Database (SVD) were used. Five datasets of voice samples were used from these databases, including normal and abnormal samples, Cysts, Vocal Nodules, Polyp, and Paralysis vocal fold. To the best of the authors’ knowledge, very few studies were done on multiclass classifications using specific pathology database. File-based and frame-based investigation for two-class and multiclass were considered. In the two-class analysis using the DT-CWPT with entropies, the classification accuracy of 100% and 99.94% was achieved for MEEI and SVD database respectively. Meanwhile, the classification accuracy for multiclass analysis comprised of 99.48% for the MEEI database and 99.65% for SVD database. The experimental results using the proposed features provided promising accuracy to detect the presence of diseases in vocal fold.
A new approach for speaker and accent recognition based on wavelets, namely Discrete Wavelet Packet (DWPT), Dual Tree Complex Wavelet Packet Transform (DT- CWPT) and Wavelet Packet Transform (WPT) based non-linear features are investigated. The results are compared with conventional MFCC and LPC features. k-Nearest Neighbors (k-NN), Support Vector Machine (SVM) and Extreme Learning Machine (ELM) classifier are used to quantify the speaker and accent recognition rate. The database for the research was developed using English digits (0~9) and Malay words. The highest accuracy for speaker recognition obtained is 93.54% while for accent recognition; it is 95.86% using Malay words. Combination of features for speaker recognition is obtained from ELM classifier is 98.68 % and for accent recognition is 98.75 % using Malay words.