Enhancing Quranic Recitation Accuracy Using State-of-the-Art Audio Classification Techniques
Abstract
- In this study, we investigate the potential of using state-of-the-art neural network architectures to increase the accuracy in classification of Quranic recitations per verse. Using a dataset of more than 4000 audio recordings annotated with rich metadata, the research has concentrated on differentiating accurate recitations through Hukm Al-Noon Al-Mushaddah specifications. This study uses three pre-trained deep learning models (Inception-V3, EfficientNet and MobileNet), as well as hybrid model proposed in this paper to perform classification of recitations. The raw audio inputs were converted into spectrograms for feature extraction and classification in each of the models. Experiments demonstrate that through the fusion, this hybrid model significantly outperforms individual predictions by dramatically improving precision, recall and F1-scores in five different verses. The total accuracy for the proposal model is 0.79 which is the highest comparing with Inception-V3 was 0.75 and EfficientNet was 0.73. The results underline the ability of such systems to provide immediate feedback for learners and thereby assist them in adhering to traditional recitation standards, a feature that helps maintain the originality of Quranic recitation. To enable usage on real data, further work should build a bigger dataset (samples of data) and optimize the model to providing feedback with larger latency
Keywords
Full Text:
PDFReferences
Al-Kaf, H., Sulong, M., Joret, A., Aminuddin, N., & Mohammad, C. (2021). Qvr: quranic verses recitation recognition system using pocketsphinx. Journal of Quranic Sciences and Research, 02(02). https://doi.org/10.30880/jqsr.2021.02.02.004.
Aljohani, N. and Jaha, E. (2023). Visual lip-reading for quranic arabic alphabets and words using deep learning. Computer Systems Science and Engineering, 46(3), 3037-3058. https://doi.org/10.32604/csse.2023.037113.
Bettayeb, N. and Guerti, M. (2020). Speech synthesis system for the holy quran recitation. The International Arab Journal of Information Technology, 18(1), 8-15. https://doi.org/10.34028/iajit/18/1/2
Bezoui, M., Elmoutaouakkil, A., & Beni‐Hssane, A. (2016). Feature extraction of some quranic recitation using mel-frequency cepstral coeficients (mfcc).. https://doi.org/10.1109/icmcs.2016.7905619
Khelifa, M., Belkasmi, M., Elhadj, Y., & Yousfi, A. (2017). Strategies for implementing an optimal asr system for quranic recitation recognition. International Journal of Computer Applications, 172(9), 35-41. https://doi.org/10.5120/ijca2017915209
Mahjoob, M., Nejati, J., & Bakhshani, N. (2014). The effect of holy quran voice on mental health. Journal of Religion and Health, 55(1), 38-42. https://doi.org/10.1007/s10943-014-9821-7
Nayef, E. and Nubli, A. (2018). The effect of recitation quran on the human emotions. International Journal of Academic Research in Business and Social Sciences, 8(2). https://doi.org/10.6007/ijarbss/v8-i2/3852
Qayyum, A., Latif, S., & Qadir, J. (2018). Quran reciter identification: a deep learning approach.. https://doi.org/10.1109/iccce.2018.8539336
Alkhateeb, J. H. (2020). A machine learning approach for recognizing the Holy Quran reciter. International Journal of Advanced Computer Science and Applications/International Journal of Advanced Computer Science & Applications, 11(7). https://doi.org/10.14569/ijacsa.2020.0110735
Samara, G., Al-Daoud, E., Swerki, N., & Alzu’bi, D. (2023). The recognition of Holy Qur’an reciters using the MFCCS’ technique and deep learning. Advances in Multimedia, 2023, 1–14. https://doi.org/10.1155/2023/2642558
Hadiyansah, R., & Andamira, R. (2023). Convolutional Neural Network (CNN) for detecting Al-Qur’an reciting and memorizing. Khazanah Journal of Religion and Technology, 1(2), 44–48. https://doi.org/10.15575/kjrt.v1i2.235
Harere, A.A., & Jallad, K.A. (2023). Quran Recitation Recognition using End-to-End Deep Learning. ArXiv, abs/2305.07034.
Saber, H., Younes, A., Osman, M., & Elkabani, I. (2024). Quran reciter identification using NASNetLarge. Neural Computing & Applications, 36(12), 6559–6573. https://doi.org/10.1007/s00521-023-09392-1
Hanna, M., Ban SH., & Basim M. (2024). A Deep learning Approach for Recognizing the Noon Rule for Reciting Holy Quran. PROtek : Jurnal Ilmaish Teknik Elektro. Vol. 11, No. 2, pp 74-80. http://doi.org/10.33387/protk.v1i2.7026
Mahmoud, A., Noor, A., & Ismail H. (2018). " Using Deep Learning for Automatically Determining Correct Application of Basic Quranic Recitation Rules". The International Arab Journal of Information and Technology, Vol. 15, No. 3A, pp 620 – 625.
Khalid M., Moyawiah, A., Ahmad M., Rafat ,A., & Iyad A. (2019). A Holy Quran Reader/Reciter Identification System Using Support Vector Machine", International Journal of Machine Learning and Computing, Vol. 9, No. 4, pp 458 – 464.
Bilal, Y., Akram M., & Amina, A. (2018). Holy Qur’an speech recognition system distinguishing the type of recitation, International Conference on Computer Science and Information technology (CSIT), Vol. 2 , No. 1, pp. 1–6.
DOI: https://doi.org/10.33387/protk.v12i3.8514
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
| Journal Policies | Submissions | People | Information |
Editorial Office :
Address: Jusuf Abdulrahman 53 Gambesi, Ternate City, Indonesia.
Email: protek@unkhair.ac.id, WhatsApp: +6282292852552