Automatic Detection of Some Tajweed Rules

correct understanding of the Holy Quran is an essential duty for all Muslims. Tajweed rules guide the reciter to perform Holy Quran reading exactly as it was uttered by Prophet Muhammad peace be upon him. This work focused on the recognition of one Quranic recitation rule. Qalqalah rule is applied to five letters of the Arabic Alphabet (Baa/Daal/Jeem/Qaaf/Taa) having sukun vowelization. The proposed system used the Mel Frequency Cepstral Coefficients (MFCC) as the feature extraction technique, and the Convolutional Neural Networks (CNN) model was used for recognition. The available dataset consists of 3322 audio samples from different surahs of the Quran for four professional readers (Sheihk) AlHussary, AlMinshawy, Abdel Baset, and Ayman Swayed. The best results were gained using Ayman Swayed audio samples with a validation accuracy of 90.8%.