e-ISSN: Applied
editor@ijaida.com | editor.ijaida@gmail.com

Intelligent Polyphonic Music Generation Using Large Language Models and Transformer-Based Sequence Learning

Puteri Amirah Ismail
Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Malaysia Muhammad Arif
Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Malaysia
Vol 1 No 1 (2026): Volume 1, Issue 1, 2026 (July-August) Pages: 36-48 Type: Research Article Published: 18-08-2026 DOI: 10.47001/IJAIDA/2026.101005

Abstract

Artificial Intelligence (AI) has significantly transformed the field of music generation by enabling machines to compose melodies, harmonies, and complete musical arrangements with minimal human intervention. Among various music generation tasks, polyphonic music generation remains one of the most challenging due to the simultaneous interaction of multiple musical voices, harmonic structures, rhythmic dependencies, and long-term compositional coherence. Traditional rule-based and statistical methods often struggle to capture the complexity of polyphonic compositions. Recent advancements in Large Language Models (LLMs), particularly Generative Pre-trained Transformer (GPT) architectures, have demonstrated exceptional capabilities in sequence modeling and creative content generation. This research investigates a GPT-based polyphonic music generation algorithm that leverages transformer architectures to learn musical representations from large-scale symbolic music datasets. The proposed framework utilizes MIDI-based music encoding, tokenization strategies, transformer-based sequence modeling, and autoregressive generation techniques to create coherent polyphonic musical compositions. Experimental analysis demonstrates that the GPT-based model effectively captures harmonic progression, rhythmic consistency, and melodic structure while generating musically plausible outputs. The study highlights the potential of large language models in computational creativity and intelligent music composition systems.

Keywords

Polyphonic Music Generation, GPT, Large Language Models, Transformer Architecture, Artificial Intelligence, Computational Creativity, MIDI, Deep Learning

Citation of this Article

Puteri Amirah Ismail, & Muhammad Arif. (2026). Intelligent Polyphonic Music Generation Using Large Language Models and Transformer-Based Sequence Learning. International Journal of Artificial Intelligence and Data Analytics, 1(1), 36-48. DOI: https://doi.org/10.47001/IJAIDA/2026.101005

References

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). "Attention Is All You Need." Advances in Neural Information Processing Systems (NeurIPS), 30, 5998–6008.
Radford, A., Narasimhan, K., Salimans, T., & Sutskever, I. (2018). "Improving Language Understanding by Generative Pre-Training." OpenAI Technical Report.
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., et al. (2020). "Language Models are Few-Shot Learners." Advances in Neural Information Processing Systems (NeurIPS), 33, 1877–1901.
Huang, C. Z. A., Vaswani, A., Uszkoreit, J., Shazeer, N., Simon, I., Hawthorne, C., et al. (2019). "Music Transformer: Generating Music with Long-Term Structure." International Conference on Learning Representations (ICLR).
Payne, C. (2019). "MuseNet: Generating Music with Large-Scale Transformer Models." OpenAI Research Report.
Agostinelli, A., Denk, T. I., Borsos, Z., Engel, J., Verzetti, M., Caillon, A., et al. (2023). "MusicLM: Generating Music From Text." International Conference on Machine Learning (ICML).
Copet, J., Kreuk, F., Gat, I., Remez, T., Kant, D., Synnaeve, G., Adi, Y., & Défossez, A. (2023). "Simple and Controllable Music Generation." Advances in Neural Information Processing Systems (NeurIPS).
Dhariwal, P., Jun, H., Payne, C., Kim, J. W., Radford, A., & Sutskever, I. (2020). "Jukebox: A Generative Model for Music." arXiv preprint arXiv:2005.00341.
Dong, H. W., Hsiao, W. Y., Yang, L. C., & Yang, Y. H. (2018). "MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment." Proceedings of the AAAI Conference on Artificial Intelligence, 32(1), 34–41.
Huang, Y. S., & Yang, Y. H. (2020). "Pop Music Transformer: Beat-Based Modeling and Generation of Expressive Pop Piano Compositions." Proceedings of the ACM International Conference on Multimedia, 1180–1188.
Hadjeres, G., Pachet, F., & Nielsen, F. (2017). "DeepBach: A Steerable Model for Bach Chorales Generation." International Conference on Machine Learning (ICML), 1362–1370.
Roberts, A., Engel, J., Raffel, C., Hawthorne, C., & Eck, D. (2018). "A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music." International Conference on Machine Learning (ICML).
Yang, L. C., Chou, S. Y., & Yang, Y. H. (2017). "MidiNet: A Convolutional Generative Adversarial Network for Symbolic-Domain Music Generation." Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 324–331.
Oore, S., Simon, I., Dieleman, S., Eck, D., & Simonyan, K. (2018). "This Time with Feeling: Learning Expressive Musical Performance." Neural Computing and Applications, 32, 955–967.
Payne, C., & Eslami, M. (2020). "Generative Models for Symbolic Music Composition." IEEE Transactions on Multimedia.
Shaw, P., Uszkoreit, J., & Vaswani, A. (2018). "Self-Attention with Relative Position Representations." Proceedings of NAACL-HLT, 464–468.
Chen, K., Wu, Y., Liu, H., Nezhurina, M., Berg-Kirkpatrick, T., & Dubnov, S. (2020). "Music AutoBot: Generating Music with Learned Representations." Proceedings of the International Society for Music Information Retrieval Conference (ISMIR).
Ens, J., & Pasquier, P. (2021). "Building the MetaMIDI Dataset: A Large-Scale MIDI Dataset for Symbolic Music Generation." Proceedings of the International Society for Music Information Retrieval Conference (ISMIR).
Lan, Y. H., Hsiao, W. Y., Cheng, H. C., & Yang, Y. H. (2024). "MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation." arXiv preprint arXiv:2407.15060.
Copet, J., Kreuk, F., Gat, I., Remez, T., Kant, D., Synnaeve, G., et al. (2023). "MusicGen: A Simple and Controllable Music Generation Model." Meta AI Research.
Agostinelli, A., Denk, T., Borsos, Z., Engel, J., Verzetti, M., Caillon, A., et al. (2023). "MusicLM and the Future of Text-to-Music Generation." Google Research.
Schneider, F., Jin, Z., & Schuller, B. (2023). "Deep Generative Models for Music and Audio Generation: A Survey." IEEE Access.
Huang, R., & Yang, J. (2023). "Transformer-Based Approaches for Symbolic Music Generation: A Survey." ACM Computing Surveys.
Choi, K., Fazekas, G., & Sandler, M. (2019). "Text-Based LSTM Networks for Automatic Music Generation." Proceedings of ISMIR.
Raffel, C., & Ellis, D. P. W. (2015). "Feed-Forward Networks with Attention for Music Generation." International Conference on Music Information Retrieval (ISMIR).
Dieleman, S., van den Oord, A., & Simonyan, K. (2018). "The Challenge of Generative Music Modeling." Deep Learning and Music Workshop.
Van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., et al. (2016). "WaveNet: A Generative Model for Raw Audio." arXiv preprint arXiv:1609.03499.
Défossez, A., Copet, J., Synnaeve, G., & Adi, Y. (2023). "High Fidelity Neural Audio Compression." Transactions on Machine Learning Research.
Borsos, Z., Marinier, R., Vincent, D., Kharitonov, E., Pietquin, O., Sharifi, M., et al. (2022). "AudioLM: A Language Modeling Approach to Audio Generation." IEEE/ACM Transactions on Audio, Speech, and Language Processing.
License: This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0).