An Exhaustive Survey to Understand Music Generation based on Artificial Intelligence
Keywords:
Artificial Intelligence, Music Generation, Deep Learning, Reinforcement Learning, Transformer ModelAbstract
Music generation is a creative process that requires the ability to understand melody, rhythm, harmony, structure, and emotional expression. Although music has long been viewed as a human-centered artistic domain, the development of Artificial Intelligence has opened new opportunities for automatic music generation with minimal human intervention. This study aims to analyze the use of AI algorithms in music generation, identify commonly used approaches, and examine existing gaps in producing high-quality musical compositions. The study reviews several AI-based methods, including recurrent neural networks, Deep Composer, WaveNet, memetic algorithms, generative adversarial networks, reinforcement learning, and transformer-based models. In addition, publicly available music datasets and GAN-based synthetic data generation are considered to support the training process. The findings indicate that deep learning models are effective in learning musical patterns, while reinforcement learning and transformer-based preprocessing can improve sequence understanding, adaptability, and structural coherence. However, current models still face challenges in duplicating specific artist styles, maintaining complete song structure, and generating music with strong uniqueness. Therefore, integrating deep learning, reinforcement learning, GAN-based synthetic data, and transformer preprocessing offers a promising direction for improving AI-generated music quality and supporting future research in automatic music composition.
Downloads
References
[1] H. Tang, Y. Gu, and X. Yang, “Music generation with ai technology: Is it possible?” in 2022 IEEE 5th International Conference on Electronics Technology (ICET). IEEE, 2022, pp. 1265–1272.
[2] L. Wang, Z. Zhao, H. Liu, J. Pang, Y. Qin, and Q. Wu, “A review of intelligent music generation systems,” Neural Computing and Applications, vol. 36, no. 12, pp. 6381–6401, 2024.
[3] A. Dash and K. Agres, “Ai-based affective music generation systems: A review of methods and challenges,” ACM Computing Surveys, vol. 56, no. 11, pp. 1–34, 2024.
[4] United Nations Department of Economic and Social Affairs, “The 17 goals,” https://sdgs.un.org/goals, 2026, accessed: 2026-03-13.
[5] D. T. Ng, E. H. Ng, and S. K. Chu, “Engaging students in creative music making with musical instrument application in an online flipped classroom,” Education and information Technologies, vol. 27, no. 1, pp. 45–64, 2022.
[6] R. Mitra and I. Zualkernan, “Music generation using deep learning and generative ai: a systematic review,” IEEE Access, vol. 13, pp. 18 079–18 106, 2025.
[7] S. Kosasi, C. Lukita, M. H. R. Chakim, A. Faturahman, and D. A. R. Kusumawardhani, “The influence of digital artificial intelligence technology on quality of life with a global perspective,” Aptisi Transactions on Technopreneurship (ATT), vol. 5, no. 3, pp. 240–250, 2023, https://doi.org/10.34306/att.v5i3.354.
[8] A. Valavanidis, “Artificial intelligence (ai) applications,” Department of Chemistry, National and Kapodistrian University of Athens, University Campus Zografou, vol. 15784, 2023.
[9] V. Meilinda, L. W. Ming, M. Muhtarom, J. Zanubiya, M. R. Kusuma, and R. Yaputra, “Artificial intelligence and iot integration for intelligent decision-making systems,” Sundara Advanced Research on Artificial Intelligence, vol. 2, no. 1, pp. 1–13, 2026.
[10] T.-C. Pricop and A. Iftene, “Music generation with machine learning and deep neural networks,” Procedia Computer Science, vol. 246, pp. 1855–1864, 2024.
[11] F. B. Ismail, A. T. Z. Xuan, U. Rusilowati, and J. Williams, “Exploring the frontier of data science: Innovations, challenges, and future directions,” International Transactions on Education Technology (ITEE), vol. 2, no. 2, pp. 163–172, 2024.
[12] Y. Lin, “Gan-based model for multi-instrument collaborative music generation using deep learning,” Informatica, vol. 50, no. 5, 2026.
[13] J. Galajda and K. Hua, “Neural-base music generation for intelligence duplication,” arXiv preprint arXiv:2310.13691, 2023.
[14] M. Zhang, “Advancing deep learning for expressive music composition and performance modeling,” Scientific Reports, vol. 15, no. 1, p. 28007, 2025.
[15] F. P. Oganda, P. Pandey, S. Wulandari, S. Audiah, and Y. M. Kareem, “Human centered analysis of digital technology and community social well being,” Journal of Orange Technology, vol. 2, no. 1, pp. 37–47, 2025.
[16] N. D. Noviati, F. E. Putra, S. Sadan, R. Ahsanitaqwim, N. Septiani, and N. P. L. Santoso, “Artificial intelligence in autonomous vehicles: Current innovations and future trends,” International Journal of Cyber and IT Service Management (IJCITSM), vol. 4, no. 2, pp. 97–104, 2024.
[17] A. Muhamed, L. Li, X. Shi, S. Yaddanapudi, W. Chi, R. Suresh, Z. Lipton, and A. Smola, “Transformergan: symbolic music generation using a learned loss,” 4th Workshop on Machine Learning for Creativity and Design at NeurIPS 2020, 2020, accessed: 2026-03-13.
[18] B. Yu, P. Lu, R. Wang, W. Hu, X. Tan, W. Ye, S. Zhang, T. Qin, and T.-Y. Liu, “Museformer: Transformer with fine-and coarse-grained attention for music generation,” Advances in neural information processing systems, vol. 35, pp. 1376–1388, 2022.
[19] J. E. Galajda, B. Royal, and K. A. Hua, “Deep composer: A hash-based duplicative neural network for generating multi-instrument songs,” in 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 2021, pp. 7961–7968.
[20] B. Rawat, U. Rahardja, M. Hardini, and A. R. Dina, “Driver drowsiness detection using novel deep learning,” Health, Empathy, and AI Learning (HEAL), vol. 1, no. 1, pp. 1–6, 2025.
[21] C. Hernandez-Olivan and J. R. Beltran, “Music composition with deep learning: A review,” Advances in speech and music technology: computational aspects and applications, pp. 25–50, 2022.
[22] N. Azizah, P. A. Sunarya, U. Rahardja, A. B. Mutiara, P. Prihandoko, and C. Pasha, “Improving smearnegative tuberculosis detection using data augmentation and faster r-cnn,” International Journal of Cyber and IT Service Management (IJCITSM), vol. 6, no. 1, pp. 65–77, 2026.
[23] Y. Lu, L. Chen, Y. Zhang, M. Shen, H. Wang, X. Wang, C. van Rechem, T. Fu, and W. Wei, “Machine learning for synthetic data generation: a review,” arXiv preprint arXiv:2302.04062, 2023.
[24] K. Kapoor, “Music generation lstm,” Kaggle Notebook, 2021, accessed: 2026-03-13. [Online]. Available: https://www.kaggle.com/code/karnikakapoor/music-generation-lstm/data
[25] anubhavjin, “Automatic music generator dl,” Kaggle Notebook, 2021, accessed: 2026-03-13. [Online]. Available: https://www.kaggle.com/code/anubhavjin/automatic-music-generator-dl/data
[26] basu369victor, “Generate music with variational autoencoder,” Kaggle Notebook, 2022, accessed: 2026-03-13. [Online]. Available: https://www.kaggle.com/code/basu369victor/generate-music-with-variational-autoencoder/data
[27] J.-W. Chang, C.-Y. Chiou, J.-Y. Liao, Y.-K. Hung, C.-C. Huang, K.-C. Lin, and Y.-H. Pu, “Music recommender using deep embedding-based features and behavior-based reinforcement learning,” Multimedia Tools and Applications, vol. 80, no. 26, pp. 34 037–34 064, 2021.
[28] I. Rakhmatulin, M.-S. Dao, A. Nassibi, and D. Mandic, “Exploring convolutional neural network architectures for eeg feature extraction,” Sensors, vol. 24, no. 3, p. 877, 2024.
[29] Y. Zhao, M. Yang, Y. Lin, X. Zhang, F. Shi, Z. Wang, J. Ding, and H. Ning, “Ai-enabled text-to-music generation: A comprehensive review of methods, frameworks, and future directions,” Electronics, vol. 14, no. 6, p. 1197, 2025.
[30] I. Agchar, I. Baumann, F. Braun, P. A. P´erez-Toro, K. Riedhammer, S. Trump, and M. Ullrich, “A survey of music generation in the context of interaction,” arXiv preprint arXiv:2402.15294, 2024.
[31] R. Kanthavel, R. A. Freeda, and R. Dhaya, “Reinforcement learning in generative ai: State-of-the-art performance,” in Revolution with Generative AI: Trends and Techniques. Springer, 2025, pp. 65–86.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Bhupesh Rawat, Qurotul Aini, Nuke Puji Lestari Santoso, Sipho Dlamini
This work is licensed under a Creative Commons Attribution 4.0 International License.
