Dataset Ratio Experiment for Tajweed Law Recognition Using MFCC and CNN Features
DOI:
https://doi.org/10.26905/jeemecs.v8i2.15546Keywords:
Audio Classification, Convolutional Neural Network, Mel-Frequency Cepstral Coefficient, Nun Sukun, Tajwid DetectionAbstract
This research aims to develop a tajwid classification system focusing on the detection of nun sukun and tanwin rules in Quranic recitation using the Convolutional Neural Network (CNN) and Mel-Frequency Cepstral Coefficient (MFCC) methods. The dataset used includes 1,344 audio samples collected from both direct recordings and YouTube observations. Audio preprocessing involved silence removal and noise filtering, followed by feature extraction using MFCC with 40 coefficients. These features were then classified into six categories: Idghom Bighunnah, Idghom Bilaghunnah, Idzhar Halqi, Ikhfa Haqiqi, Iqlab, and No Class. The CNN architecture implemented includes three convolutional layers with Batch Normalization and Leaky ReLU activation, optimized with a softmax classifier. Three different dataset split scenarios (80:10:10, 70:15:15, and 60:20:20) were evaluated to determine the best performance. The highest accuracy of 89% was achieved using the 80:10:10 data split, with macro-average F1-score reaching 0.87. Results show that CNN combined with MFCC provides reliable classification of tajwid rules, particularly in identifying distinctive acoustic patterns. The study confirms that data partitioning significantly influences model performance and highlights the importance of optimal preprocessing and architecture selection in deep learning-based speech recognition tasks.
Downloads
References
[1] N. Rihladhatul and A. Sayoga, “AL-AFKAR : Journal for Islamic Studies The Living Qur ’ an : Ethnographic Study and Understanding of Al- Isra ’: 9 in Urban Communities,” vol. 7, no. 4, pp. 334–346, 2024, doi: 10.31943/afkarjournal.v7i4.1648.Abstract.
[2] H. Fajrussalam, W. Widaningsih, N. Nurdiansyah, L. N. Istighna, C. Nurjanah, and C. R. A. Widjaya, “Implementasi Program Maghrib Mengaji sebagai Sarana Pembelajaran Al-Quran pada Anak Usia Dini: Studi Deskriptif Kualitatif di TPQ Al Ittihad Kab. Cirebon,” At-Ta’lim Media Inf. Pendidik. Islam, vol. 22, no. 2, p. 259, 2023, doi: 10.29300/attalim.v22i2.2546.
[3] R. D. Arifin, “No Title,” Dianisa. [Online]. Available: https://dianisa.com/nun-sukun-dan-tanwin/
[4] M. H. Ashadiqi, A. Erlansari, and F. Farady, “Aplikasi Pembelajaran Tajwid Berbasis Android,” J. Rekursif, vol. 8, no. 1, pp. 59–70, 2020.
[5] A. Wirdiani, S. N. Machetho, I. K. G. D. Putra, M. Sudarma, R. S. Hartati, and H. A. Ferdian, “Improvement Model for Speaker Recognition using MFCC-CNN and Online Triplet Mining,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 14, no. 2, pp. 420–427, 2024, doi: 10.18517/ijaseit.14.2.19396.
[6] L. Syafa’ah, R. Prasetyono, and H. Hariyady, “Enhancing Qur’anic Recitation Experience with CNN and MFCC Features for Emotion Identification,” Kinet. Game Technol. Inf. Syst. Comput. Network, Comput. Electron. Control, vol. 4, no. 2, 2024, doi: 10.22219/kinetik.v9i2.2007.
[7] J. J. M. Montemayor, G. P. G. Escuadra, M. A. G. Nambatac, and D. T. Tenoria, “Detecting Rice Weevils in Stored Grains using MFCC and CNN,” Procedia Comput. Sci., vol. 234, no. 2023, pp. 1681–1688, 2024, doi: 10.1016/j.procs.2024.03.173.
[8] Z. K. Abdul and A. K. Al-Talabani, “Mel Frequency Cepstral Coefficient and its Applications: A Review,” IEEE Access, vol. 10, no. October, pp. 122136–122158, 2022, doi: 10.1109/ACCESS.2022.3223444.
[9] F. Wang and X. Shen, “Research on Speech Emotion Recognition Based on Teager Energy Operator Coefficients and Inverted MFCC Feature Fusion,” Electron., vol. 12, no. 17, 2023, doi: 10.3390/electronics12173599.
[10] S. Kulkarni, “Impact of Various Data Splitting Ratios on the Performance of Machine Learning Models in the Classification of Lung Cancer,” in Proceedings of the Second International Conference on Emerging Trends in Engineering (ICETE 2023), Springer Nature, 2023, p. 96.
[11] Y. Dokuz and Z. Tufekci, “Mini-batch sample selection strategies for deep learning based speech recognition,” Appl. Acoust., vol. 171, p. 107573, 2021, doi: 10.1016/j.apacoust.2020.107573.
[12] W. Mu, B. Yin, X. Huang, J. Xu, and Z. Du, “Environmental sound classification using temporal-frequency attention based convolutional neural network,” Sci. Rep., vol. 11, no. 1, pp. 1–14, 2021, doi: 10.1038/s41598-021-01045-4.
[13] A. P. Sari, H. Suzuki, T. Kitajima, T. Yasuno, D. A. Prasetya, and N. Nachrowie, “Prediction model of wind speed and direction using convolutional neural network - Long short term memory,” PECon 2020 - 2020 IEEE Int. Conf. Power Energy, no. 1, pp. 356–361, 2020, doi: 10.1109/PECon48942.2020.9314474.
[14] Y. Furusho and K. Ikeda, “Theoretical analysis of skip connections and batch normalization from generalization and optimization perspectives,” APSIPA Trans. Signal Inf. Process., vol. 9, 2020, doi: 10.1017/ATSIP.2020.7.
[15] Y. Liu, X. Chen, M. Cheng, C. Hsieh, Y. You, and L. Angeles, “C ONCURRENT A DVERSARIAL L EARNING FOR L ARGE -,” pp. 1–17, 2021.
[16] S. H. Golzar, H. Bagherpour, and J. A. Parian, “Research Article A New Method to Optimize Deep CNN Model for Classification of Regular Cucumber Based on Global Average Pooling,” vol. 2024, no. Dl, 2024, doi: 10.1155/2024/5818803.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 JEEMECS (Journal of Electrical Engineering, Mechatronic and Computer Science)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Our ethic statements are based on COPE’s Best Practice Guidelines for Journal Editors.
Publication decisions
The editor is responsible for deciding which of the articles submitted to the journal should be published.
The editor may be guided by the policies of the journal's editorial board and constrained by such legal requirements as shall then be in force regarding libel, copyright infringement and plagiarism. The editor may confer with other editors or reviewers in making this decision.
Fair play
An editor at any time evaluate manuscripts for their intellectual content without regard to race, gender, sexual orientation, religious belief, ethnic origin, citizenship, or political philosophy of the authors.
Confidentiality
The editor and any editorial staff must not disclose any information about a submitted manuscript to anyone other than the corresponding author, reviewers, potential reviewers, other editorial advisers, and the publisher, as appropriate.
Disclosure and conflicts of interest
Unpublished materials disclosed in a submitted manuscript must not be used in an editor's own research without the express written consent of the author.
Duties of Reviewers
Contribution to Editorial Decisions
Peer review assists the editor in making editorial decisions and through the editorial communications with the author may also assist the author in improving the paper.
Promptness
Any selected referee who feels unqualified to review the research reported in a manuscript or knows that its prompt review will be impossible should notify the editor and excuse himself from the review process.
Confidentiality
Any manuscripts received for review must be treated as confidential documents. They must not be shown to or discussed with others except as authorized by the editor.
Standards of Objectivity
Reviews should be conducted objectively. Personal criticism of the author is inappropriate. Referees should express their views clearly with supporting arguments.
Acknowledgement of Sources
Reviewers should identify relevant published work that has not been cited by the authors. Any statement that an observation, derivation, or argument had been previously reported should be accompanied by the relevant citation. A reviewer should also call to the editor's attention any substantial similarity or overlap between the manuscript under consideration and any other published paper of which they have personal knowledge.
Disclosure and Conflict of Interest
Privileged information or ideas obtained through peer review must be kept confidential and not used for personal advantage. Reviewers should not consider manuscripts in which they have conflicts of interest resulting from competitive, collaborative, or other relationships or connections with any of the authors, companies, or institutions connected to the papers.
Duties of Authors
Reporting standards
Authors of reports of original research should present an accurate account of the work performed as well as an objective discussion of its significance. Underlying data should be represented accurately in the paper. A paper should contain sufficient detail and references to permit others to replicate the work. Fraudulent or knowingly inaccurate statements constitute unethical behavior and are unacceptable.
Originality and Plagiarism
The authors should ensure that they have written entirely original works, and if the authors have used the work and/or words of others that this has been appropriately cited or quoted.
Multiple, Redundant or Concurrent Publication
An author should not in general publish manuscripts describing essentially the same research in more than one journal or primary publication. Submitting the same manuscript to more than one journal concurrently constitutes unethical publishing behaviour and is unacceptable.
Acknowledgement of Sources
Proper acknowledgment of the work of others must always be given. Authors should cite publications that have been influential in determining the nature of the reported work.
Authorship of the Paper
Authorship should be limited to those who have made a significant contribution to the conception, design, execution, or interpretation of the reported study. All those who have made significant contributions should be listed as co-authors. Where there are others who have participated in certain substantive aspects of the research project, they should be acknowledged or listed as contributors.
The corresponding author should ensure that all appropriate co-authors and no inappropriate co-authors are included on the paper, and that all co-authors have seen and approved the final version of the paper and have agreed to its submission for publication.
Disclosure and Conflicts of Interest
All authors should disclose in their manuscript any financial or other substantive conflict of interest that might be construed to influence the results or interpretation of their manuscript. All sources of financial support for the project should be disclosed.
Fundamental errors in published works
When an author discovers a significant error or inaccuracy in his/her own published work, it is the author’s obligation to promptly notify the journal editor or publisher and cooperate with the editor to retract or correct the paper.
