Please use this identifier to cite or link to this item:
|Title||Arabic Isolated Word Speaker Dependent Recognition System|
In this thesis we designed a new Arabic isolated word speaker dependent recognition system based on a combination of several features extraction and classifications techniques. Where, the system combines the methods outputs using a voting rule. The system is implemented with a graphic user interface under Matlab using G62 Core I3/2.26 Ghz processor laptop. The dataset used in this system include 40 Arabic words recorded in a calm environment with 5 different speakers using laptop microphone. Each speaker will read each word 8 times. 5 of them are used in training and the remaining are used in the test phase. First in the preprocessing step we used an endpoint detection technique based on energy and zero crossing rates to identify the start and the end of each word and remove silences then we used a discrete wavelet transform to remove noise from signal. In order to accelerate the system and reduce the execution time we make the system first to recognize the speaker and load only the reference model of that user. We compared 5 different methods which are pairwise Euclidean distance with MelFrequency cepstral coefficients (MFCC), Dynamic Time Warping (DTW) with Formants features, Gaussian Mixture Model (GMM) with MFCC, MFCC+DTW and Itakura distance with Linear Predictive Coding features (LPC) and we got a recognition rate of 85.23%, 57% , 87%, 90%, 83% respectively. In order to improve the accuracy of the system, we tested several combinations of these 5 methods. We find that the best combination is MFCC | Euclidean + Formant | DTW + MFCC | DTW + LPC | Itakura with an accuracy of 94.39% but with large computation time of 2.9 seconds. In order to reduce the computation time of this hybrid, we compare several subcombination of it and find that the best performance in trade off computation time is by first combining MFCC | Euclidean + LPC | Itakura and only when the two methods do not match the system will add Formant | DTW + MFCC | DTW methods to the combination, where the average computation time is reduced to the half to 1.56 seconds and the system accuracy is improved to 94.56%. Finally, the proposed system is good and competitive compared with other previous researches.
|Publisher||الجامعة الإسلامية - غزة|
|Files in this item|