Applied and Computational Engineering

- The Open Access Proceedings Series for Conferences


Proceedings of the 3rd International Conference on Signal Processing and Machine Learning

Series Vol. 5 , 31 May 2023


Open Access | Article

Deep learning in automatic music generation

Yizhen Zhang * 1
1 Fu Foundation School of Engineering and Applied Science, New York City, NY 10027, US.

* Author to whom correspondence should be addressed.

Applied and Computational Engineering, Vol. 5, 87-92
Published 31 May 2023. © 2023 The Author(s). Published by EWA Publishing
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Citation Yizhen Zhang. Deep learning in automatic music generation. ACE (2023) Vol. 5: 87-92. DOI: 10.54254/2755-2721/5/20230539.

Abstract

Music is a grouping of musical tones from various frequencies. While artists composed through a deliberate arrangement of different notes, nowadays, A.I. programs learn to automatically generate short music through a machinal sequence of distinct notes. This essay compared the utility and efficiency of traditional machine learning (Regression Model) and deep learning methods (LSTM). This research only focused on instrumental classical music and used the MusicNet collection as the primary dataset. The comprehensive experiments are conducted from these two models, which suggests two results. Firstly, the LSTM model generates melodies that better fit the training styles. Secondly, models are better fitted on single music data than on the entire dataset.

Keywords

Deep learning, Automatic Music Generation, LSTM, Regression Model.

References

1. Zachary. (November, 2020). “How I Built a Lo-Fi Hip-Hop Music Generator.” Medium. Artificial Intelligence in Plain English. https://ai.plainenglish.io/building-a-lo-fi-hip-hop-generator-e24a005d0144.

2. Pai, Aravindpai. (January, 2021). “Automatic Music Generation: Music Generation Deep Learning.” Analytics Vidhya. https://www.analyticsvidhya.com/blog/2020/01/how-to-perform-automatic-music-generation/.

3. Skúli, Sigurður. (December, 2017). “How to Generate Music Using a LSTM Neural Network in Keras.” Medium. Towards Data Science.

4. Yang, Li-Chia, Szu-Yu Chou, and Yi-Hsuan Yang. (July, 2017). “Midinet: A Convolutional Generative Adversarial Network for Symbolic-Domain Music Generation.” arXiv.org.

5. Hsiao, Li-Chia Yang, and Yi-Hsuan Yang. (November, 2021). “Musegan: Multi-Track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment.” arXiv.org. https://arxiv.org/abs/1709.06298.

6. Tham, Isaac. (August, 2021). “Generating Music Using Deep Learning.” Medium. Towards Data Science. https://towardsdatascience.com/generating-music-using-deep-learningcb5843a9d55e.

7. Chen, Vivian, Jackson DeVico, Arianna Reischer, Leo Stepanewk, Ananya Vasireddy, Nicholas Zhang, and Sabar Dasgupta. (2020). “Random Forest Regression of Markov Chains for Accessible Music Generation.” 2020 IEEE MIT Undergraduate Research Technology Conference (URTC).

8. Gomes, Sara. (November, 2021). “Music Generation Based on Classics .” Kaggle. Kaggle. https://www.kaggle.com/code/smogomes/music-generation-based-on-classics.

9. T, Smitha., and V. Sundaram. (2012). “Classification Rules by Decision Tree for Disease Prediction.” International Journal of Computer Applications 43, no. 8: 6–12. https://doi.org/10.5120/6121-8323.

10. Rácz, Bajusz, and Héberger. (August, 2019). “Multi-Level Comparison of Machine Learning Classifiers and Their Performance Metrics.” Molecules 24, no. 15 (2019): 2811. https://doi.org/10.3390/molecules24152811.

Data Availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series 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 series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series'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 series.

3. 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 (See Open Access Instruction).

Volume Title
Proceedings of the 3rd International Conference on Signal Processing and Machine Learning
ISBN (Print)
978-1-915371-57-7
ISBN (Online)
978-1-915371-58-4
Published Date
31 May 2023
Series
Applied and Computational Engineering
ISSN (Print)
2755-2721
ISSN (Online)
2755-273X
DOI
10.54254/2755-2721/5/20230539
Copyright
© 2023 The Author(s)
Open Access
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Copyright © 2023 EWA Publishing. Unless Otherwise Stated