Evaluation of the Pronunciation of Tajweed Rules Based on DNN as a Step Towards Interactive Recitation Learning

Abstract

Proper recitation of the Quran, adhering to the rules of Tajweed, is crucial for preventing mistakes during recitation and requires significant effort to master. Traditional methods of teaching these rules are limited by the availability of qualified instructors and time constraints. Automatic evaluation of recitation can address these challenges by providing prompt feedback and supporting independent practice. This study focuses on developing a deep learning model to classify three Tajweed rules—separate stretching (Al Mad), tight noon (Ghunnah), and hide (Ikhfaa)—using the publicly available QDAT dataset, which contains over 1,500 audio recordings. The input data consisted of audio recordings from this dataset, transformed into normalized mel-spectrograms. For classification, the EfficientNetB0 architecture was used, enhanced with a Squeeze-and-Excitation block. The developed model achieved accuracy rates of 95.35 %,${9 9. 3 4 \%}$, and${9 7. 0 1 \%}$for the respective rules. An analysis of the learning curves confirmed the model's robustness and absence of overfitting. The proposed approach demonstrates high efficiency and paves the way for developing interactive educational systems for Tajweed study.

More by Selcuk Cankurt

• Effects of Binary Similarity Metrics on Energy Consumption During Recommendation by Using Collaborative Filtering ApproachJournal of sustainable development issues. · 2026
• STUDENT PERFORMANCE PREDICTION USING MACHINE LEARNINGZenodo · 2026
• Interpretable Hybrid CNN-BiLSTM-Attention Model for ECG Arrhythmia ClassificationIEEE International Conference on Smart Information Systems and Technologies · 2026
• COLLABORATIVE MULTI-AGENT CHATBOT FRAMEWORK FOR INTELLIGENT TUTORING AND FEEDBACKZenodo · 2026