A Study on Music Composition through Reinforcement Learning 


Vol. 45,  No. 3, pp. 521-528, Mar.  2020
10.7840/kics.2020.45.3.521


PDF
  Abstract

In this paper, we propose a new approach to music composition through the image recognition and reinforcement-learning and we conducted a study to creating music, excluding musical knowledge and human intuition, and described the results. The proposed learning environment in this paper, is a new differentiated approach to extract the information of a sheet music using image recognition-related technologies, unlike studies based on Sound Recognition that focus on sound waves. also, we designing an architecture of learning environment that utilizes two different actors, proposing a more in-depth approach than a traditional Markov Chain. thus, we detail the proposed structure and methodology. These experiments will be a cornerstone for research to advancement in the future works and It will be direction of our future research to improve it.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

T. Jung, S. Lee, K. Kim, "A Study on Music Composition through Reinforcement Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 3, pp. 521-528, 2020. DOI: 10.7840/kics.2020.45.3.521.

[ACM Style]

Tack-hyun Jung, Seung-ho Lee, and Keecheon Kim. 2020. A Study on Music Composition through Reinforcement Learning. The Journal of Korean Institute of Communications and Information Sciences, 45, 3, (2020), 521-528. DOI: 10.7840/kics.2020.45.3.521.

[KICS Style]

Tack-hyun Jung, Seung-ho Lee, Keecheon Kim, "A Study on Music Composition through Reinforcement Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 3, pp. 521-528, 3. 2020. (https://doi.org/10.7840/kics.2020.45.3.521)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880