Model Konversi Notasi Kepatihan ke dalam Format MIDI untuk Pembangkitan Musik Barat Orisinal
DOI:
https://doi.org/10.33633/tc.v21i3.6672Keywords:
algorithmic composition, pembangkitan musik orisinal, LSTM, MIDI, GamelanAbstract
Musik orisinal merupakan komposisi baru yang diciptakan dengan memodifikasi elemen-elemen musik menggunakan metode yang belum pernah dilakukan sebelumnya. Penelitian ini bertujuan untuk mengembangkan sistem pembangkitan musik Barat orisinal yang diukur berdasarkan pola urutan nada dan distribusinya yang diakuisisi dari musik Gamelan, musik tradisional dari Jawa. Lembar musik Gamelan yang digunakan sebagai sumber data dikonversi ke dalam format MIDI untuk dijadikan input bagi pelatihan jaringan LSTM berdasarkan informasi nada, langkah dan durasi. Selanjutnya, teknik sequence prediction digunakan untuk membangkitkan output nada berdasarkan input nada sebelumnya. Hasil pembangkitan musik Barat orisinal berupa data dalam format file MIDI dan visualisasinya dalam format notasi Balok. Evaluasi pada pelatihan jaringan LSTM menunjukkan hasil yang baik dengan tingkat loss sebesar 0,1. Evaluasi tingkat kemiripan pola urutan nada dan distribusinya dilakukan menggunakan grafik distribusi sampel nada, langkah dan durasi, dan hasilnya menunjukkan tingkat kemiripan yang baik.References
J. Wang, X. Wang dan J. Cai, 2019, Jazz Music Generation Based on Grammar and LSTM, dalam 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), pp. 115-120. Doi: 10.1109/IHMSC.2019.00035.
H. Zhu, Q. Liu, N.J. Yuan, C. Qin, J. Li, K. Zhang, G. Zhou, F. Wei, Y. Xu dan E. Chen, 2008, XiaoIce Band: A Melody and Arrangement Generation Framework for Pop Music, dalam KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, July 2018, London United Kingdom, pp. 2837-2846. Doi: 10.1145/3219819.3220105
C-Z. A. Huang, C. Hawthorne, A. Roberts, M. Dinculescu, J. Wexler, L. Hong dan J. Howcroft, 2019, The Bach Doodle: Approachable Music Composition with Machine Learning at Scale, dalam 20th International Society for Music Information Retrieval Conference, Delft, The Netherlands, 2019.
S. Dai, Z. Jin, C. Gomes dan R.B. Dannenberg, 2021, Controllable Deep Melody Generation via Hierarchical Music Structure Representation, dalam Proc. of the 22nd Int. Society for Music Information Retrieval Conf., Online, 2021.
K. Hastuti, A. Azhari, A. Musdholifah dan R. Supanggah, 2017, Rule-Based and Genetic Algorithm for Automatic Gamelan Music Composition, International Review on Modelling and Simulations, vol. 10, no. 3, pp. 202-2017, 2017, Doi: 10.15866/iremos.v10i3.11479.
A. Ayd?ngün, D. Ba?datl?o?lu, B. Canbaz, A. Kökb?y?k, M.F. Yavuz, N. Bölücü dan B. Can, 2020, Turkish Music Generation using Deep Learning, 28th Signal Processing and Communications Applications Conference (SIU), 2020, pp. 1-4. Doi: 10.1109/SIU49456.2020.9302283.
C. Donahue, H.H. Mao, Y.E. Li, G.W. Cottrell dan J. McAuley, 2019, LakhNES: Improving multi-instrumental music generation with cross-domain pre-training, dalam 20th International Society for Music Information Retrieval Conference, Delft, Netherlands, 2019.
S. Lattner, M. Grachten dan G. Widmer, 2018, Imposing higher-level structure in polyphonic music generation using convolutional restricted boltzmann machines and constraints, Journal of Creative Music Systems, vol. 2, 2018, pp. 1-31.
https://www.openmicuk.co.uk/advice/how-to-be-original/, diakses pada tanggal 2 Juli 2022.
H.T. Hung, C.Y. Wang, Y.H. Yang dan H.M. Wang, 2019, Improving Automatic Jazz Melody Generation by Transfer Learning Techniques, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 339-346, doi: 10.1109/APSIPAASC47483.2019.9023224.
A. Ranjan, V.N.J. Behera dan M. Reza, 2020, Using a Bi-directional LSTM Model with Attention Mechanism trained on MIDI Data for Generating Unique Music, arXiv:2011.00773 [cs.SD]. Doi: 10.48550/arXiv.2011.00773.
A.A.S. Gunawan, A.P. Iman dan D. Suhartono, 2020, Automatic Music Generator Using Recurrent Neural Network, International Journal of Computational Intelligence Systems, vol. 13, no. 1, pp. 645–654. Doi: 10.2991/ijcis.d.200519.001.
F. Shah, T. Naik dan N. Vyas, 2019, LSTM Based Music Generation, 2019 International Conference on Machine Learning and Data Engineering (iCMLDE), pp. 48-53. Doi: 10.1109/iCMLDE49015.2019.00020.
K. Munkhbat, B. Jargalsaikhan, T. Amarbayasgalan, N. Theera-Umpon dan K.H. Ryu, 2021, Emotional Piano Melodies Generation Using Long Short-Term Memory, dalam N.T. Nguyen, S. Chittayasothorn, D. Niyato, B. Trawi?ski (eds), Intelligent Information and Database Systems ACIIDS 2021. Lecture Notes in Computer Science(), vol 12672. Springer, Cham. https://doi.org/10.1007/978-3-030-73280-6_53.
A. E. Memi? dan V. H. Yalim Keles, 2021, Piano Music Generation with a Text Based Musical Note Representation using LSTM Models, 29th Signal Processing and Communications Applications Conference (SIU), pp. 1-4. Doi: 10.1109/SIU53274.2021.9477952.
Z. Huang, X. Jia dan Y. Guo, 2019, State-of-the-Art Model for Music Object Recognition with Deep Learning, Appl. Sci., vol. 9, no. 13, 2645. Doi: 10.3390/app9132645.
M. Rantina, H. Hasmalena dan Y. Yosef, 2020, Development of Children’s Songs Using Musescore Applications in Learning Aspect of Development for Early Childhood, International Conference on Elementary Education, vol. 2, no. 1, pp. 889-892.
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Khafiizh Hastuti, Arry Maulana Syarif, Syafira Rosa Amalia, Muhammad Adrian Surya Saputra, Adam Zufar Majid Suprayogi, Afinzaki Amiral, Labib Ahnaf Dhiyaul Khoir

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
License Terms
All articles published in Techno.COM Journal are licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This means:
1. Attribution
Readers and users are free to:
-
Share – Copy and redistribute the material in any medium or format.
-
Adapt – Remix, transform, and build upon the material.
As long as proper credit is given to the original work by citing the author(s) and the journal.
2. Non-Commercial Use
-
The material cannot be used for commercial purposes.
-
Commercial use includes selling the content, using it in commercial advertising, or integrating it into products/services for profit.
3. Rights of Authors
-
Authors retain copyright and grant Techno.COM Journal the right to publish the article.
-
Authors can distribute their work (e.g., in institutional repositories or personal websites) with proper acknowledgment of the journal.
4. No Additional Restrictions
-
The journal cannot apply legal terms or technological measures that restrict others from using the material in ways allowed by the license.
5. Disclaimer
-
The journal is not responsible for how the published content is used by third parties.
-
The opinions expressed in the articles are solely those of the authors.
For more details, visit the Creative Commons License Page:
? https://creativecommons.org/licenses/by-nc/4.0/