Advertisement

Automatic Jazz Melody Composition Through a Learning-Based Genetic Algorithm

  • Yong-Wook Nam
  • Yong-Hyuk KimEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11453)

Abstract

In this study, we automate the production of good-quality jazz melodies through genetic algorithm and pattern learning by preserving the musically important properties. Unlike previous automatic composition studies that use fixed-length chromosomes to express a bar in a score, we use a variable-length chromosome and geometric crossover to accommodate the variable length. Pattern learning uses the musical instrument digital interface data containing the jazz melody; a user can additionally learn about the melody pattern by scoring the generated melody. The pattern of the music is stored in a chord table that contains the harmonic elements of the melody. In addition, a sequence table preserves the flow and rhythmic elements. In the evaluation function, the two tables are used to calculate the fitness of a given excerpt. We use this estimated fitness and geometric crossover to improve the music until users are satisfied. Through this, we successfully create a jazz melody as per user preference and training data.

Keywords

Genetic algorithm Automatic composing Geometric crossover 

Notes

Acknowledgement

We would like to thank Prof. Francisco Fernández de Vega for providing us with much advice and help in writing this paper. This research was supported by a grant [KCG-01-2017-05] through the Disaster and Safety Management Institute funded by Korea Coast Guard of Korean government, and it was also supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No. 2015R1D1A1A01060105).

References

  1. 1.
    Montag, C., Reuter, M., Axmacher, N.: How one’s favorite song activates the reward circuitry of the brain: personality matters! Behav. Brain Res. 225(2), 511–514 (2011)Google Scholar
  2. 2.
    van Eijck, K.: Social differentiation in musical taste patterns. Soc. Forces 79(3), 1163–1185 (2001)CrossRefGoogle Scholar
  3. 3.
    Papadopoulos, G., Wiggins, G.: AI methods for algorithmic composition: a survey, a critical view and future prospects. In: AISB Symposium on Musical Creativity, vol. 124, pp. 110–117 (1999)Google Scholar
  4. 4.
    Biles, J.A.: Genjam: a genetic algorithm for generating jazz solos. In: Proceedings of the International Computer Music Association, vol. 94, pp. 131–137 (1994)Google Scholar
  5. 5.
    Matić, D.: A genetic algorithm for composing music. Yugoslav J. Oper. Res. 20(1), 157–177 (2010)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Horner, A., Goldberg, D.E.: Genetic algorithms and computer-assisted music composition. Urbana 51(61801), 437–441 (1991)Google Scholar
  7. 7.
    Quick, D.: Kulitta: A Framework for Automated Music Composition. Yale University (2014)Google Scholar
  8. 8.
    Keller, R.M., Morrison, D.R.: A grammatical approach to automatic improvisation. In: Proceedings of the Fourth Sound and Music Conference (2007)Google Scholar
  9. 9.
    Bickerman, G., Bosley, S., Swire, P., Keller, R.M.: Learning to create jazz melodies using deep belief nets. In: Proceedings of the International Conference on Computational Creativity, pp. 228–237 (2010)Google Scholar
  10. 10.
    Johnson, D.D., Keller, R.M., Weintraut, N.: Learning to create jazz melodies using a product of experts. In: Proceedings of the International Conference on Computational Creativity (2017)Google Scholar
  11. 11.
    Fernández de Vega, F.: Revisiting the 4-part harmonization problem with GAs: a critical review and proposals for improving. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 1271–1278 (2017)Google Scholar
  12. 12.
    Nam, Y.-W., Kim, Y.-H.: A geometric evolutionary search for melody composition. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 53–54 (2018)Google Scholar
  13. 13.
    Nam, Y.-W., Kim, Y.-H.: Melody composition using geometric crossover for variable-length encoding. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 37–38 (2017)Google Scholar
  14. 14.
    Johnson, D.D.: Generating polyphonic music using tied parallel networks. In: Correia, J., Ciesielski, V., Liapis, A. (eds.) EvoMUSART 2017. LNCS, vol. 10198, pp. 128–143. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-55750-2_9CrossRefGoogle Scholar
  15. 15.
    Hadjeres, G., Pachet, F.: Deepbach: a steerable model for bach chorales generation. In: Proceedings of the 34th International Conference on Machine Learning, no. 70, pp. 1362–1371 (2017)Google Scholar
  16. 16.
    Syswerda, G.: Uniform crossover in genetic algorithms. In: Proceedings of the Third International Conference on Genetic Algorithms, pp. 2–9 (1989)Google Scholar
  17. 17.
    Moraglio, A., Poli, R.: Geometric landscape of homologous crossover for syntactic trees. Evol. Comput. 1, 427–434 (2005)Google Scholar
  18. 18.
    Moraglio, A., Poli, R., Seehuus, R.: Geometric crossover for biological sequences. In: Collet, P., Tomassini, M., Ebner, M., Gustafson, S., Ekárt, A. (eds.) EuroGP 2006. LNCS, vol. 3905, pp. 121–132. Springer, Heidelberg (2006).  https://doi.org/10.1007/11729976_11CrossRefGoogle Scholar
  19. 19.
    Yoon, Y., Kim, Y.-H., Moraglio, A., Moon, B.-R.: A mathematical unification of geometric crossovers defined on phenotype space. arXiv:0907.3200 (2009)
  20. 20.
    Sells, C., Weinhardt, M.: Windows Forms 2.0 Programming (Microsoft Net Development Series). Addison-Wesley Professional, Boston (2006)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceKwangwoon UniversitySeoulRepublic of Korea

Personalised recommendations