Study of Fundamental Approaches in Regards with Automatic Music Generation using 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:

Automatic Music Generation, Stochastic Music, CNN, LSTM, WaveNet, Deep Learning architectures, WaveNet

Abstract

Computational creativity is an interdisciplinary topic in which computers attempt to achieve creative behaviors. One of the prolifest areas of music generation, which employs computer methods to make music, is known as algorithmic composition or music meta creation. It is often difficult to determine specific objectives and to monitor issues that state-of-the-art systems can deem addressed and what additional advancements will instead be necessary. In this survey, we attempt to provide people who want to study computer creativity and music production with a thorough introduction. We examine the state-of-the-art systems of Music Generation by providing instances of the primary techniques to creating music and identifying the open issues mentioned in earlier studies. We mention works that have offered answers to each of these issues and that describe what still needs to be done and suggested guidelines for additional study. This paper combined my two passions – music and deep learning – to create an automatic music generation model. We are thrilled to share our approach with you, to enable you to generate your music! We will first quickly understand the concept of automatic music generation before diving into the different approaches we can use to perform this. Finally, we will fire up Python and design our automatic music generation model.

References

  1. Amabile, T. M. (1983a). “A consensual technique for creativity assessment,” in The Social Psychology of Creativity, Springer Series in Social Psychology, ed T. M. Amabile (New York, NY: Springer), 37–63.
  2. Amabile, T. M. (1983b). The social psychology of creativity: a componential conceptualization. J. Pers. Soc. Psychol. 45, 357–376. doi: 10.1037/0022-3514.45.2.357
  3. Amabile, T. M., Conti, R., Coon, H., Lazenby, J., and Herron, M. (1996). Assessing the work environment for creativity. Acad. Manage. J. 39, 1154–1184. doi: 10.5465/256995
  4. Anders, T., and Miranda, E. R. (2011). Constraint programming systems for modeling music theories and composition. ACM Comput. Surv. 43, 1–38. doi: 10.1145/1978802.1978809
  5. Anderson, C., Eigenfeldt, A., and Pasquier, P. (2013). “The generative electronic dance music algorithmic system (GEDMAS),” in Proceedings of the Artificial Intelligence and Interactive Digital Entertainment (AIIDE'13) Conference (Palo Alto, CA), 4.
  6. Ariza, C. (2009). The interrogator as a critic: the turning test and the evaluation of generative music systems. Comput. Music J. 33, 48–70. doi: 10.1162/comj.2009.33.2.48
  7. Baer, J., and McKool, S. S. (2009). “Assessing creativity using the consensual assessment technique,” in Handbook of Research on Assessment Technologies, Methods, and Applications in Higher Education (Hershey, PA: IGI Global), 65–77.
  8. Bell, C. (2011). Algorithmic music composition using dynamic Markov chains and genetic algorithms. J. Comput. Sci. Coll. 27, 99–107.
  9. Bidlack, R. (1992). Chaotic systems as simple (but complex) compositional algorithms. Compu. Music J. 16, 33–47. doi: 10.2307/3680849
  10. Biles, J., Anderson, P., and Loggi, L. (1996). “Neural network fitness functions for a musical IGA,” in Proceedings of the Soft Computing Conference (Reading, UK), 11.
  11. Biles, J. A. (1994). “GenJam: a genetic algorithm for generating jazz solos,” in ICMC, Vol. 94 (Ann Arbor, MI), 131–137.
  12. Biles, J. A. (2001). “Autonomous GenJam: eliminating the fitness bottleneck by eliminating fitness,” in Proceedings of the 2001 Genetic and Evolutionary Computation Conference Workshop Program (San Francisco, CA), 7.
  13. Boden, M. A. (1998). Creativity and artificial intelligence. Artif. Intell. 103, 347–356. doi: 10.1016/S0004-3702(98)00055-1
  14. Boden, M. A. (2004). The Creative Mind: Myths and Mechanisms. London: Routledge.
  15. Bodily, P. M., and Ventura, D. (2018). “Musical metacreation: past, present, and future,” in Mume 2018 (Salamanca: University of Salamanca), 5.
  16. Brèmaud, P. (2013). Markov Chains: Gibbs Fields, Monte Carlo Simulation, and Queues, Vol 31. New York, NY: Springer Science & Business Media.
  17. Bringsjord, S., Bello, P., and Ferrucci, D. (2003). “Creativity, the turing test, and the (better) Lovelace test,” in The Turing Test, ed J. H. Moor (Dordrecht: Springer), 215–239.
  18. Briot, J.-P., Hadjeres, G., and Pachet, F.-D. (2017). Deep learning techniques for music generation - a survey. arXiv:1709.01620.
  19. Briot, J.-P., Hadjeres, G., and Pachet, F.-D. (2020). Deep Learning Techniques for Music Generation. Computational Synthesis and Creative Systems. Basel: Springer International Publishing.
  20. Briot, J.-P., and Pachet, F. (2018). Deep learning for music generation: challenges and directions. Neural Comput. Appl. 32, 981–993. doi: 10.1007/s00521-018-3813-6

Downloads

Published

2021-04-10

Issue

Section

Research Articles

How to Cite

[1]
Vincy Kaushik, Pravin Kumar Mishra, " Study of Fundamental Approaches in Regards with Automatic Music Generation using AI , International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011, Volume 9, Issue 1, pp.1374-1381, March-April-2021.