Session:

LBP - Late Breaking Papers

Title:

Evolutionary Music Composer

Authors:

Yaser M.A. Khalifa
Hunter Shi
Gustavo Abreu

Abstract:

In this paper, an autonomous intelligent music composition tool was developed using Genetic Algorithms. The research has been structured into two phases, each of which builds upon the previous one. The first phase of the project was to develop more sophisticated fitness measures for the genetic algorithm, with the goal of applying data compression techniques to identify musically sound patterns in music through music theory principles. In the second phase, methods to use weighted permutations of different fitness functions and generated motifs were explored. These combinations were evaluated and as a result, musically fit patterns were generated. Four musical phrases are generated at the end of each program run, each phrase consists of eight measures, and each measure is one motif of up to eight notes. The generated music piece will be translated through an additional algorithm into Guido Music Notation (GMN) files for further evaluation and alternate representation (midi). The Evolutionary Music Composer (EMC) was able to create interesting pieces of music that were both innovative and musically sound.