Makhraj recognition using speech processing

This paper present new application of recitation verification based on correct makhraj. Traditionally, people have learned from the expert person to recite al-Quran correctly with a long duration. In this work, a new way to learn reciting the al-Quran is proposed in order to reduce the duration of learning from the expert. A system using Mel Frequency Cepstrum Coefficient (MFCC) as feature extraction and Mean Square Error (MSE) as a pattern matching technique is considered in order to develop a makhraj recognition system. An experimental setup trying to measure the system performance in terms of accuracy based on False Reject Rate (FRR) and Wrong Recognition (WR). The FRR obtained is 0% and gives 100% of accuracy.