MAKHRAJ ‘AIN PRONUNCIATION ERROR DETECTION USING MEL FREQUENCY CEPSTRAL COEFFICIENT AND MODIFIED VGG-16

Abstract

Based on research conducted by the Institute of Qur'anic Sciences (IIQ) as many as 65% of Muslims in Indonesia are illiterate in the Qur'an. In previous studies, research was conducted on the detection of Arabic word pronunciation errors against non-natives using the Mel Frequency Cepstral Coefficient (MFCC) and Support Vector Machine (SVM) methods with a test result of 54.6%. Due to the low accuracy results in previous studies, this study aims to design and build a system that can correct the accuracy of the pronunciation of makhraj letter ‘ain with the method used is a combination of MFCC and Convolutional Neural Network (CNN) with a vgg-16 structure that has been modified. The dataset used is 1,600 voice recordings divided into two categories of the correct pronunciation of the letter ‘ain and incorrect pronunciation of the letter ‘ain and four variations of pronunciation with different vowels with a total data of 800 records in each category. This study conducted several experiments on variations of the CNN kernel. The results of the training model that produced the best accuracy in all variations were the training model on kernels 16, 32, 64 with a final accuracy rate of 100% for all variations with 96% accuracy validation. In the fathah variation, the validation accuracy is 94%. In the variation of dhommah and the variation of kasrah obtained a validation accuracy of 97%. Therefore, this study succeeded in distinguishing the sound of the pronunciation of the letter ‘ain with different vowels and measuring the accuracy of the pronunciation of the letter ‘ain. Implementing the modified vgg-16 produces high accuracy and validation values for each speech variation during the model train process.