Soft Computing for Music Generation using Genetic Algorithm

Abstract

Creating good music is truly a laborious task since it requires lots of effort, extended time, and many instruments. When the tune of music does not sound good after being composed with much toil, then composers must discard it, which is a hectic job. Hence, an easy way to compose the music which will require less time and less effort is required. Genetic algorithm is a possible way of searching the solution to the problem in large dimension search space. Genetic algorithm (GA), a part of soft computing in the field of music composition can be used to solve this issue. This paper proposes the use of GA for composing music and the use of fitness function to select more melodious music. In GA, for music creation, two musical segments will act as parent nodes for creating new music, and by applying genetic operators, there is a change in the music such that breaks are modified between the tunes. Music which sounds pleasing is chosen with the user’s help using fitness function, and if the user is satisfied with the generated tune, then the process of generating the music is terminated; otherwise, the selected musical tune by the fitness function will act as the parent node for the next generation of musical tune. Moreover, this work explains which fitness function to be applied on the specific problem.