Sistem Bantu Verifikasi Irama Hafalan Nadzam Aqidatul Awam
DOI:
https://doi.org/10.29407/ywt8d283Abstract
Kegiatan menghafal Nadzam Aqidatul Awam di pondok pesantren umumnya masih dinilai secara manual. Penelitian ini mengusulkan sistem verifikasi irama hafalan otomatis menggunakan metode Siamese Long Short-Term Memory (LSTM) berbasis ekstraksi ciri hibrida (MFCC, Delta, Delta-Delta, dan kontur pitch YIN). Dataset terdiri dari 400 audio rekaman 20 santri Pondok Pesantren Al Ma’ruf Kedunglo dengan acuan irama Ustadz Muhammad Shabri. Pengujian objektif menggunakan data uji terisolasi di Jupyter Notebook menghasilkan akurasi 92%, presisi 88%, recall 96%, dan F1-score 92%. Namun, pengujian real-time pada antarmuka Streamlit menunjukkan variasi performa akibat environmental noise dan perbedaan kualitas mikrofon (hardware gain). Riset ini berhasil memberikan kontribusi ilmiah dalam memperluas kapabilitas sistem verifikasi suara otomatis ke ranah penilaian estetika keselarasan ketukan irama tradisional keagamaan secara presisi.
Keywords:
Audio Signal Processing, Confusion Matrix, MFCC, Nadzam Aqidatul Awam, Siamese LSTM##plugins.themes.default.displayStats.downloads##
References
[1] N. Fazwanis, B. Othman, M. F. Bin, and M. Yusof, ―Utilising Dialogical Pedagogy as a
Mode of Instruction with the Purpose of Improving Future Islamic Education through the
Study of Qur ’ anic Principles,‖ vol. 13, no. 10, pp. 394–400, 2023, doi:
10.6007/IJARBSS/v13-i10/18784.
[2] P. Pembelajaran, K. Aqidatul, P. N.- Nilai, T. Santri, M. Diniyah, and T. Qulub, ―R eslaj :
Religion Education Social Laa Roiba Journal R eslaj : Religion Education Social Laa
Roiba Journal,‖ vol. 7, pp. 2363–2375, 2025, doi: 10.47476/reslaj.v7i8.9318.
[3] A.-Q. U. R. An, D. I. Pondok, and A. Mu, ―Tradisi sima’an dalam penguatan hafalan alqur’an di pondok pesantren,‖ vol. 2, no. 2, pp. 309–320, 2025, doi:
10.63424/amsal.v2i2.375.
[4] S. Alharbi et al., ―Automatic Speech Recognition : Systematic Literature Review,‖ IEEE
Access, vol. PP, p. 1, 2021, doi: 10.1109/ACCESS.2021.3112535.
[5] S. Mariyanto, A. Sasongko, S. Tsaury, S. Ariessaputra, and S. Ch, ―Mel Frequency
Cepstral Coefficients ( MFCC ) Method and Multiple Adaline Neural Network Model for
Speaker Identification,‖ vol. 7, no. December, 2023, doi: 10.62527/joiv.7.4.1376.
[6] H. Yakura, K. Watanabe, and M. Goto, ―Self-Supervised Contrastive Learning for,‖
IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. 30, pp. 1614–1623, 2022, doi:
10.1109/TASLP.2022.3169627.
[7] A. Zahra, D. Nur, A. Jl, L. Pol, S. No, and K. P. Utara, ―Analisa Perbandingan
Penggunaan Metodologi Pengembangan Perangkat Lunak ( Waterfall , Prototype ,
Iterative , Spiral , Rapid Application Development ( RAD )),‖ no. 4, 2024, doi:
10.61132/merkurius.v2i4.148.
[8] Z. K. Abdul and A. K. Al-talabani, ―Mel Frequency Cepstral Coefficient and its
applications : A Review,‖ IEEE Access, vol. PP, p. 1, 2022, doi:
10.1109/ACCESS.2022.3223444.
[9] R. Sebastian and S. O. Keefe, ―Bridging Biological Hearing and Neuromorphic
Computing : End-to-End Time-Domain Audio Signal Processing with Reservoir
Computing‖, doi: 10.48550/arXiv.2603.24283.
[10] F. Islam, N. Parvin, M. Rahman, T. Ahmed, D. Chakraborty, and S. Rahman,
―Fundamental Frequency Extraction by Utilizing the Combination of Spectrum in Noisy
Speech,‖ vol. 13, no. 4, pp. 730–734, doi: 10.37391/IJEER.130413.
[11] N. Sharma et al., ―Siamese Convolutional Neural Network-Based Twin Structure Model
for Independent Offline Signature Verification,‖ pp. 1–14, 2022, doi:
10.3390/su141811484.
[12] Y. Lu, Y. Xu, E. Herrera-viedma, and Y. Han, ―Consensus of large-scale group decision
making in social network : the minimum cost model based on robust optimization,‖ Inf.
Sci. (Ny)., vol. 547, pp. 910–930, 2021, doi: 10.1016/j.ins.2020.08.022.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
