Advertisement

Automation of Musical Compositions Synthesis Process Based on Neural Networks

  • Nikita Nikitin
  • Vladimir RozalievEmail author
  • Yulia Orlova
  • Alla Zaboleeva-Zotova
Conference paper
  • 7 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1156)

Abstract

This work is devoted to development and approbation of the methods for automated sound generation based on image color spectrum with using the neural networks. The work contains a description of the transition between color and music characteristics, the rationale for choosing and the description of a used neural network. The choice of the neural network implementation technology is described. It also contains the detailed description about the experiments to choose the best neural network parameters.

Keywords

Automated music generation HSV color space Newton correlation table J. Caivano correlation scheme Image analysis Sound synthesis Recurrent neural network 

References

  1. 1.
    Ariza, C.: Two pioneering projects from the early history of computer-aided algorithmic composition. Comput. Music J. 35(3), 40–56 (2012)CrossRefGoogle Scholar
  2. 2.
    Chereshniuk, I.: Algorithmic composition and its role in modern musical education. Art Educ. (3), 65–68 (2015)Google Scholar
  3. 3.
    Acar, I.H.: Early childhood development and education through nature-child interactions: a conceptual paper. Int. J. Educ. Researchers 4(2), 1–10 (2013)MathSciNetGoogle Scholar
  4. 4.
    Koops, H.V., Magalhaes, P., Bas de Haas, W.: A functional approach to automatic melody harmonisation. In: Proceedings of the First ACM SIGPLAN Workshop on Functional Art, Music, Modeling & Design, FARM 2013, pp. 47–58. ACM (2013)Google Scholar
  5. 5.
    Mazurowski, L.: Computer models for algorithmic music composition. In: Proceedings of the Federated Conference on Computer Science and Information Systems, pp. 733–737 (2012)Google Scholar
  6. 6.
    Palmer, E., Schloss, K., Xu, Z., Prado-León, L.: Music–color associations are mediated by emotion. Duke-National University of Singapore Graduate Medical School (2013)Google Scholar
  7. 7.
    Doornbusch, P.: Gerhard Nierhaus: algorithmic composition: paradigms of automated music generation. Comput. Music J. 34(3) (2014)Google Scholar
  8. 8.
    Brinkkemper, F.: Analyzing Six Deep Learning Tools for Music Generation. http://www.asimovinstitute.org/analyzing-deep-learning-tools-music/. Accessed 04 May 2019
  9. 9.
    Kline, D.M.: Revisiting squared-error and cross-entropy functions for training neural network classifiers. https://link.springer.com/article/10.1007/s00521-005-0467-y/. Accessed 04 May 2019
  10. 10.
    Fernández, J.D., Vico, F.: AI methods in algorithmic composition: a comprehensive survey. J. Artif. Intell. Res. 48, 513–582 (2013)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Waite, E., Eck, D., Roberts, A., Abolafia, D.: Project magenta: generating long-term structure in songs and stories (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Nikita Nikitin
    • 1
  • Vladimir Rozaliev
    • 1
    Email author
  • Yulia Orlova
    • 1
  • Alla Zaboleeva-Zotova
    • 1
  1. 1.Volgograd State Technical UniversityVolgogradRussia

Personalised recommendations