Abstract
Chinese Folk Drum music is an excellent traditional cultural resource, it has brilliant historical and cultural heritage and excellent traditional cultural connotation. However, the survey found that the social and cultural values, tourism economic values, and national self-confidence embodied in folk drum music, such as Xi'an drum music, are far from being released, and even its own inheritance and development are facing difficulties. The research focuses on the automatic generation of Xi'an drum music, with the aim of further inheriting, developing, and utilizing this exceptional traditional cultural resource. While Artificial Intelligence (AI) music generation has gained popularity in recent years, most platforms primarily focus on modern music rather than Chinese folk music. To address these issues and the unique challenges faced by Xi'an drum music, this paper proposes a Bi-LSTM network-based deep reinforcement learning model. The model incorporates the distinctive characteristics of ancient Chinese music, such as pitch, chord, and mode, and utilizes the Actor-Critic algorithm in reinforcement learning. During the simulation generation stage, an improved method of generating strategies through reward and punishment scores is introduced. Additionally, the model takes into account abstract concept constraints, such as chord progression and music theory rules, which are translated into computer language. By constructing a chord reward mechanism and a music principle reward mechanism, the model achieves harmony constraints and enables the systematic generation of drum music. Experimental results demonstrate that the proposed model, based on Bi-LSTM deep reinforcement learning, can generate Xi'an drum music with high quality and artistic aesthetics. This research contributes to the preservation, development, and utilization of Xi'an drum music, leveraging advancements in AI music generation technology.
Similar content being viewed by others
Data availability
The data that support the findings of this study are openly available in Internet.
References
Ping Z, Zhe C, Guiling Y (2020) Research on the protection and inheritance of Xi’an drum music intangible cultural heritage [J]. Cooperative Economy and Technology 16:20–22. https://doi.org/10.13665/j.cnki.hzjjykj.2020.16.007
Chordia P, Sastry A, Şentürk S (2011) Predictive tabla modelling using variable-length markov andhidden markov models[J]. J New Music Res 40(2):105–118
Pachet F, Roy P (2011) Markov constraints: steerable generation of markov sequences[J]. Constraints 16(2):148–172
Briot J (2020) From artificial neural networks to deep learning for music generation: history, concepts and trends[J]. Neural Comput Appl 33(1):39–65
Shopynskyi M, Golian N, Afanasieva I (2020) Long short term memory model appliance for generating music compositions. 2020 IEEE international conference on problems of infocommunications. Science and Technology, Kharkiv, Ukraine, pp 239–242. https://doi.org/10.1109/PICST51311.2020.94
Dan M, Yue W (2021) Overview of intelligent music production based on generation countermeasure network [J]. Res Comput Appl 38(03):641–646. https://doi.org/10.19734/j.issn.1001-3695.2020.02.0030
Eck D, Schmidhuber J (2008) A first look at music composition using LSTM recurrent neural networks. Idsia Usi Supsi Instituto Dalle Molle, Lugano
Oord A, Dieleman S, Zen H et al (2016) WaveNet: a generative model for raw audio[J]. CoRR,2016,abs/1609.03499. https://doi.org/10.48550/arXiv.1609.03499
Yang LC, Chou SY, Yang YH (2017) MidiNet: a convolutional generative adversarial network for symbolic-domain music generation using 1D and 2D conditions[J]. https://doi.org/10.48550/arXiv.1703.10847
Dong HW, Hsiao WY, Yang LC et al (2018) MuseGAN: Symbolic-domain music generation and accompaniment with multi-track sequential generative adversarial networks[J]. https://doi.org/10.48550/arXiv.1709.06298
Briot J-P, Hadjeres G, Pachet F-D (2020) Deep learning techniques for music generation, vol 1. Springer, Heidelberg
Huang CZA, Vaswani A, Uszkoreit J et al (2018) Music transformer: generating music with long-term structure (2018) [J]. arXiv preprint arXiv:1809.04281
Roberts A, Engel J, Raffel C et al (2018) A hierarchical latent vector model for learning long-term structure in music[C]. International Conference on Machine Learning, pp 4364–4373. Applications, 2020, 32(9): 4773–4784
Shahriar S, Al Roken N (2022) How can generative adversarial networks impact computer generated art? Insights from poetry to melody conversion. Int J Inf Manag Data Insights 2(1):100066
Carnovalini F, Rodà A (2020) Computational creativity and music generation systems: an introduction to the state of the art. Front Artif Intell 3:14
Moysis L et al (2023) Music deep learning: deep learning methods for music signal processing—a review of the state-of-the-art. IEEE Access 11:17031–17052. https://doi.org/10.1109/ACCESS.2023.3244620
Casella P, Paiva A (2001) Magenta: an architecture for real time automatic composition of background music[C]. International Workshop on Intelligent Virtual Agents, Berlin, pp 224–232
Ghedini F, Pachet F, Roy P (2016) Creating music and texts with flow machines. In: Corazza G, Agnoli S (eds) Multidisciplinary contributions to the science of creative thinking. Creativity in the Twenty First Century. Springer, Singapore. https://doi.org/10.1007/978-981-287-618-8_18
Huang YS, Yang YH (2020) Pop music transformer: beat-based modeling and generation of expressive pop piano compositions[C]. Proceedings of the 28th ACM international conference on multimedia, pp 1180–1188
Nan N, Guan X, Wang Y et al (2022) Common quantitative characteristics of music melodies—pursuing the constrained entropy maximization casually in composition[J]. Sci China Inf Sci 65(7):174201
Liu J, Dong Y, Cheng Z et al (2022) Symphony generation with permutation invariant language model[J]. arXiv preprint arXiv:2205.05448
Zhang N (2020) Learning adversarial transformer for symbolic music generation [J]. IEEE Trans Neural Netw Learn Syst 34(4):1754–1763. https://doi.org/10.1109/TNNLS.2020.2990746
Guan F, Yu C, Yang S. A GAN model with self-attention mechanism to generate multi-instruments symbolic music[C]. 2019 international joint conference on neural networks. https://doi.org/10.1109/IJCNN.2019.8852291
Shahriar S (2022) GAN computers generate arts a survey on visual arts, music, and literary text generation using generative adversarial network. Displays 73:102237
Luo J et al (2020) MG-VAE: deep Chinese folk songs generation with specific regional styles. Proceedings of the 7th Conference on Sound and Music Technology (CSMT) Revised Selected Papers. Springer Singapore
Zhengyu C, Kunqi Y (2016) A review of MIDI music theory in the new era [J]. Art Rev 23:3. https://doi.org/10.3969/j.issn.1008-3359.2016.23.039
Yuanyue T (2020) Research on folk song composition based on Markov model and neural network[D]. South China University of Technology. https://doi.org/10.27151/d.cnki.ghnlu.2020.002944
Haodong Z (2022) Comparison of Characteristics between Jiangzhou Drum Music and Xi’an Drum Music [J]. Voice of the Yellow River 11:32–34. https://doi.org/10.19340/j.cnki.hhzs.2022.11.015
Liyun W (2015) Research on the color grading function of Chinese national pentatonic “partial tone” in melody[J]. Northern Music 000(007):128–130
Tingge W (1987) Viewing the relationship between Traditional Music and Contemporary Music Creation from Chinese Piano Music [J]. Chinese Musicology 03:79–85
Iliadis LA, Sotiroudis SP, Kokkinidis K, Sarigiannidis P, Nikolaidis S, Goudos SK (2022) Music deep learning: a survey on deep learning methods for music processing. 2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST), Bremen, Germany, pp 1–4. https://doi.org/10.1109/MOCAST54814.2022.9837541
Sajad S, Dharshika S, Meleet M (2021) Music generation for novices using Recurrent Neural Network (RNN). 2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Chennai, India, pp 1–6. https://doi.org/10.1109/ICSES52305.2021.9633906
Remesh A, K AP, Sinith MS (2022) Symbolic domain music generation system based on LSTM architecture. 2022 Second International Conference on Next Generation Intelligent Systems (ICNGIS), Kottayam, India, pp 1–4. https://doi.org/10.1109/ICNGIS54955.2022.10079872
Zou Y, Zou P, Zhao Y et al (2021) MELONS: generating melody with long-term structure using transformers and structure graph[J]. https://doi.org/10.48550/arXiv.2110.05020
Hochreiter S, Schmidhuber J (1997) Long short-term memory[J]. Neural Comput 9(8):1735–1780
Rajadhyaksha M, Lakhani N, Mudassir MA, Bhavathankar P (2022) Music generation with bi-directional long short term memory neural networks. 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kharagpur, India, pp 1–6
Cho K, Van Merriënboer B, Gulcehre C et al (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. arXiv preprint ar Xiv:1406.1078
Tao W, Cong J, Xiaobing L, Yun T, Lin Q (2021) Multi track music generation countermeasure network based on transformer [J]. Comput Appl 41(12):3585–3589
Qiu Y (2019) Research on music generation based on generative adversarial network[D]. University of Electronic Science and Technology of China
Yong B (2020) Research and implementation of music generation based on deep reinforcement learning[D]. Zhengzhou University. https://doi.org/10.27466/d.cnki.gzzdu.2020.000157
Dua M, Yadav R, Mamgai D, Brodiya S (2020) An improved RNN-LSTM based novel approach for sheet music generation[J]. Procedia Comput Sci 171(C):465–474
Yong B, Lin Q (2020) Yun music generation based on reinforcement learning actor- critic algorithm[J]. Comput Appl Softw 37(05):118–122+182
Chengai S, Xinfeng Z, Gang T (2019) Music generation based on reward value RNN and A2C model [J]. Software 40(07):96–99
Haoyu G, Lifeng C, Niangrong G (2022) Li Jiahao 5G URLLC bearer network slice traffic scheduling optimization based on reinforcement learning [J]. Comput Knowl Technol 18(13):9–13. https://doi.org/10.14004/j.cnki.ckt.2022.0883
Haibin L (2022) Application of reinforcement learning in single-track music generation[D]. University of Chinese Academy of Sciences (Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences). https://doi.org/10.27822/d.cnki.gszxj.2022.000129
Ji S, Luo J, Yang X (2020) A comprehensive survey on deep music generation: multi-level representations, algorithms, evaluations, and future directions[J]. https://doi.org/10.48550/arXiv.2011.06801
Ting G (2021) Research and implementation of music melody generation algorithm based on deep learning[D]. Beijing University of Posts and Telecommunications. https://doi.org/10.26969/d.cnki.gbydu.2021.001784
Dannenberg RB (2015) Music understanding and the future of music performance[J]
Shuntaro O, Masayuki O, Shinichiro T (2019) Efficient partition of integer optimization problems with one-hot encoding[J]. Sci Rep 9(1):13036
Zheng M (2021) A method of generating Chinese pop music melody[C]. Technical Committee on Control Theory, Chinese Association of Automation, Chinese Association of Automation, Systems Engineering Society of China. School of Information Science and Technology, University of Science and Technology of China. https://doi.org/10.26914/c.cnkihy.2021.028723
Acknowledgements
This work is partly supported by the key laboratory funds of the Ministry of Culture and Tourism under grant No 2022-13, the National Natural Science Foundation of China under Grant No. 62377034, 61977044, the Shaanxi Key Science and Technology Innovation Team Project under Grant No. 2022TD-26, the key project of teaching management reform in Shaanxi Normal University under Grant No. 22GX-JG05.
Author information
Authors and Affiliations
Contributions
Li Peng: Preparation, creation and/or presentation of the published work by those from the original research group, specifically critical review, commentary or revision – including pre-or postpublication stages.
Liang Tian-mian: Ideas; formulation or evolution of overarching research goals and aims; Programming, software development; designing computer programs; implementation of the computer code and supporting algorithms; testing of existing code components; Writing—Original Draft.
Cao Yu-mei: Verification, whether as a part of the activity or separate, of the overall replication/ reproducibility of results/experiments and other research outputs.
Wang Xiao-ming: Oversight and leadership responsibility for the research activity planning and execution, including mentorship external to the core team.
Wu Xiao-jun: Management and coordination responsibility for the research activity planning and execution.
Lei Lin-yi: Provision of study resources.
Corresponding author
Ethics declarations
Ethical and informed consent for data used
Informed consent.
Competing interests
The authors declared that they have no conflicts of interest to this work.We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, P., Liang, Tm., Cao, Ym. et al. A novel Xi’an drum music generation method based on Bi-LSTM deep reinforcement learning. Appl Intell 54, 80–94 (2024). https://doi.org/10.1007/s10489-023-05195-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-05195-y