<![CDATA[Memorizing the Qur'an is a highly recommended act of worship for Muslims, yet traditional learning methods often face constraints such as the limited availability of competent teachers. This research aims to develop and measure the performance of an automated system for testing the memorization of Surah Yasin (verses 1-83) through voice recognition using the Discrete Cosine Transform (DCT) method. The DCT method is applied to convert voice signals from the time domain to the frequency domain, extracting unique features from each verse to be compared with reference voice samples. The system was tested on all 83 verses using 6 training voice samples and 4 test voice samples per verse, totaling 830 samples. System performance was evaluated using four variations of probability constants (error tolerance): 0.3, 0.4, 0.5, and 0.6. The results indicate that the probability constant significantly affects the system's accuracy. The detection rates achieved were 70.2% (constant 0.3), 84.6% (constant 0.4), 89.8% (constant 0.5), and peaked at 93.4% (constant 0.6). With an overall average detection rate of 84.5%, the DCT method is proven effective, and the developed system has strong potential as a reliable aid for Qur'an memorizers.]]>
Copyrights © 2026
