Development of Symbolic Music Generation Technique Based on Deep Learning and AI

Authors

  • Vincy Kaushik  Bharat Institute of Technology, Meerut, Uttar Pradesh, India
  • Pravin Kumar Mishra  Assistant Professor, Bharat Institute of Technology, Meerut, Uttar Pradesh, India

Keywords:

Symbolic Music Generation, AI, Deep Learning, MIDI

Abstract

In this work we propose MusPy, a Python open source toolkit for the creation of symbolic music. MusPy provides easy to use tools for key music generating components like dataset administration, data I/O, data preparation, and model assessment. We offer the statistical analysis of the eleven presently supported MusPy datasets to demonstrate their potential. Moreover, by training an autoregressive model on each dataset, we undertake a cross-data generalisation experience and measure the likelihood of the rest — a process made easy by a MusPy dataset management system. The results reveal a domain map that overlaps different frequently used data sets with more cross-gender examples in some data sets than in other. These results might serve as a reference for selecting data sets in future study, alongside the examination of data sets.

References

  1. J.P. Briot, G. Hadjeres, and F. Pachet, “Deep learning techniques for music generation: A survey,” arXiv preprint arXiv:1709.01620, 2017.
  2. A. Hankinson, P. Roland, and I. Fujinaga, “The music encoding initiative as a document-encoding framework,” in Proc. of the 12th International Society for Music Information Retrieval Conference (ISMIR), 2011.
  3. R. M. Bittner, M. Fuentes, D. Rubinstein, A. Jansson, K. Choi, and T. Kell, “mirdata: Software for reproducible usage of datasets,” in Proc. of the 20th International Society for Music Information Retrieval Conference (ISMIR), 2019.
  4. A. Roberts, J. Engel, C. Raffel, C. Hawthorne, and
  5. D. Eck, “A hierarchical latent vector model for learning long-term structure in music,” in Proc. of the 35th International Conference on Machine Learning (ICML), 2018.
  6. S. Oore, I. Simon, S. Dieleman, D. Eck, and K. Simonyan, “This time with feeling: Learning expressive musical performance,” Neural Computing and Applications, vol. 32, 2018.
  7. C. Z. A. Huang, A. Vaswani, J. Uszkoreit, I. Simon, C. Hawthorne, N. Shazeer, A. M. Dai, M. D. Hoffman, M. Dinculescu, and D. Eck, “Music transformer: Generating music with long-term structure,” in Proc. of the 7th International Conference for Learning Representations (ICLR), 2019.
  8. C. Donahue, H. H. Mao, Y. E. Li, G. W. Cottrell, and J. McAuley, “Lakhnes: Improving multi-instrumental music generation with cross-domain pre-training,” in Proc. of the 20th International Society for Music Information Retrieval Conference (ISMIR), 2019.
  9. Y.S. Huang and Y.-H. Yang, “Pop music transformer: Generating music with rhythm and harmony,” arXiv preprint arXiv:2002.00212, 2020.
  10. O. Mogren, “C-RNN-GAN: Continuous recurrent neural networks with adversarial training,” in NeuIPS Worshop on Constructive Machine Learning, 2016.
  11. L.C. Yang, S.-Y. Chou, and Y.-H. Yang, “Midinet: A convolutional generative adversarial network for symbolic-domain music generation,” in Proc. of the 18th International Society for Music Information Retrieval Conference (ISMIR), 2017.
  12. H.W. Dong, W.-Y. Hsiao, L.-C. Yang, and Y.-H. Yang, “MuseGAN: Multi-track sequential generative adversarial networks for symbolic music generation and accompaniment,” in Proc. of the 32nd AAAI Conference on Artificial Intelligence (AAAI), 2018.
  13. L.C. Yang and A. Lerch, “On the evaluation of generative models in music,” Neural Computing and Applications, vol. 32, pp. 4773–4784, 2018.
  14. M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, and X. Zheng, “TensorFlow: A system for large-scale machine learning,” in Proc. of the 12th USENIX Symp. on Operating Systems Design and Implementation (OSDI), 2016.
  15. C. Mckay and I. Fujinaga, “JSymbolic: A feature extractor for MIDI files, C. Raffel, “Learning-based methods for comparing sequences, with applications to audio-to-MIDI alignment and matching,” Ph.D. dissertation, Columbia University, 2016.
  16. C. Hawthorne, A. Stasyuk, A. Roberts, I. Simon, C.-Z. A. Huang, S. Dieleman, E. Elsen, J. Engel, and D. Eck, “Enabling factorized piano music modeling and generation with the MAESTRO dataset,” in Proc. of the 7th International Conference on Learning Representations (ICLR), 2019.
  17. C. Donahue, H. H. Mao, and J. McAuley, “The NES music database: A multi-instrumental dataset with expressive performance attributes,” in Proc. of the 19th International Society for Music Information Retrieval Conference (ISMIR), 2018.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2021-06-30

Issue

Volume 8, Issue 3, May-June-2021

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Vincy Kaushik, Pravin Kumar Mishra, " Development of Symbolic Music Generation Technique Based on Deep Learning and AI " International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 8, Issue 3, pp.01-09, May-June-2021.