Automatic Generation of Musical Tone Row and Rhythm Based on the Twelve-Tone Technique Using Genetic Algorithm
Yoichiro Maeda and Yusuke Kajihara
Dept. of Human and Artificial Intelligent Systems, Graduate School of Engineering, University of Fukui, 3-9-1 Bunkyo, Fukui-shi, Fukui 910-8507, Japan
Genetic Algorithms (GA) and Interactive Genetic Algorithms (IGA) used to generate sound in computer applications generating music are difficult to use, as is, in directly composing music. We propose music composition based on the 12-Tone Technique (TTT). In TTT composition, the melody and rhythm are usually created separately. The melody is created first to determine the musical subject and atmosphere. We design a fitness function based on the relationship between consonant and dissonant intervals that are a part of general musical theory and generate the 12-Tone (TT) row automatically by searching for consonant tone rows using the GA. We then set a fitness function for evaluating the rhythm we define, and obtained musical rhythm using the GA.
-  N. Tokui and H. Iba, “Music Composition by Means of Interactive GA and GP,” Proc. of IEEE Systems, Man and Cybernetics, 2001.
-  D. Ando, P. Dahlstedt, M. G. Nordahl, and H. Iba, “Computer Aided Composition for Contemporary Classical Music By means of Interactive GP,” The J. of the Society for Art and Science, Vol.4, No.2, pp. 77-87, 2002. (in Japanese)
-  M. Unehara and T. Onisawa, “Composition of Music Using Human Evaluation,” Fuzzy Systems, 2001. The 10th IEEE Int. Conf. on, Vol.3, pp. 1203-1206, 2001.
-  T. Unemi and M. Senda, “A Study on Building a Support System for Music Composition by Simulated Breeding Method : Extension to Multi-part,” IPSJ SIG Notes, Vol.2002, No.40, pp. 133-188, 2002. (in Japanese)
-  M. Tokumaru, N. Muranaka, and S. Imanishi, “Continuous Expression System Repeating “Memory and Forgetfulness” : Application to a Music Composition System Using Chaotic Neural Network with Rememorizing Patterns,” J. of Japan Society for Fuzzy Theory and Intelligent Informatics, Vol.19, No.3, pp. 299-312, 2007. (in Japanese)
-  K. Ishizuka and T. Onisawa, “Generation of Variations on Theme Music Based on Impressions of Story Scenes,” ACM Int. Conf. Proc. Series, Vol.223, pp. 129-136, 2006.
-  M. Yamamoto and Y. Maeda, “Interactive Kansei System for Sound Generation Based on Network of Chaotic Elements,” Proc. of the Fourth Int. Symposium on Human and Artificial Intelligence Systems: From Control to Autonomy (HART 2004), pp. 315-320, 2004.
-  Y. Maeda, T. Niwa, and M. Yamamoto, “Interactive Chaotic Sound Generation System by Using Globally Coupled Map and Incorporation of Musical Factors,” J. of Japan Society for Fuzzy Theory and Intelligent Informatics, Vol.18, No.4, pp. 507-518, 2006. (in Japanese)
-  Y. Maeda and S. Miyashita, “Chaotic Interactive Sound Generation System Using Interactive Genetic Algorithm,” J. of Japan Society for Fuzzy Theory and Intelligent Informatics, Vol.21, No.5, pp. 768-781, 2009. (in Japanese)
-  J. Rufer, “Composition with Twelve Notes Related Only to One Another,” Greenwood Pub Group, 1979.
-  Y. Maeda and Y. Kajihara, “Automatic Generation Method of Twelve Tone Row for Musical Composition Used Genetic Algorithm,” Proc. of the IEEE Int. Conf. on Fuzzy Systems (FUZZ-IEEE 2009), pp. 963-968, 2009.
-  I. M. Oliver, D. J. Smith, and J. R. C. Holland, “A Study of Permutation Crossover Operators on the Traveling Salesman Problem,” Proc. of the Second Int. Conf. on Genetic Algorithms on Genetic algorithms and their application, pp. 224-230, 1987.
-  S. Kusamichi, “Melody composition,” Ongakunotomo-Sha, Japan, 2001. (in Japanese)