Automatic Composition System Based on Melodic Outlines and Music Theory

Automatic Composition System Based on Melodic Outlines and Music Theory

Takayuki Yoshida (Kyoto Institute of Technology, Kyoto, Japan), Teruhisa Hochin (Graduate School of Information Science, Kyoto Institute of Technology, Kyoto, Japan) and Hiroki Nomiya (Graduate School of Information Science, Kyoto Institute of Technology, Kyoto, Japan)
Copyright: © 2018 |Pages: 13
DOI: 10.4018/IJSI.2018100106

Abstract

The purpose of this article is to compose music clips satisfying selected ambience on an intended melody easily, and to get the satisfaction of self-making. The targets are beginners of music theory. To achieve those purposes, this article proposes the automatic composing system that takes impression words and outlines, which represent the melody's profile lines, as inputs. This system makes several arrangements and modifications to the initial melody based on the music theory. It is experimentally clarified that the music clips composed by the system are satisfactory, and their moods fit the specified impression words.
Article Preview
Top

Automatic Composition

Many automatic composition methods have been proposed (Kitahara & Miyama, 2015). A method used music knowledge (Kobayashi & Ogata, 2002). Some methods used genetic algorithm (Imai & Nagao, 1998; Nakamura & Onisawa 2009). Sumita and Hayashi (2008) used Markov random field. Otani et al. (2013) used Harmony Search in creating the rhythm of melody. Tokumaru et al. (1997) used fuzzy reasoning.

Although automatic composition is possible, there is a drawback that melody depends on training data sets or music knowledge. Improving the composition strategy requires more learning or more knowledge. Moreover, the melody generated may not agree with the user’s intention and/or taste. We need the method that the user’s intention and/or taste can directly be reflected in the music piece generated. The method proposed in this paper enables it by using a melodic outline described later.

Usage of Affective Information

Some methods use the affective information of users. Otani et al. (2013) aimed at the automatic composition according to the user’s sensitivity. Nakamura and Onisawa (2007) proposed the automatic composition based on the user’s impression.

Music pieces give us some impression. Affective information should be used. We use impression words as affective information.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 9: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 8: 4 Issues (2020): 3 Released, 1 Forthcoming
Volume 7: 4 Issues (2019)
Volume 6: 4 Issues (2018)
Volume 5: 4 Issues (2017)
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing