Automatic Evolutionary Music Composition Based on Multi-objective Genetic Algorithm

This paper presents a multi-objective approach for making melody compositions in evolutionary music. There exist several methods to generate music based on computer algorithms, but they cannot deal with multi-dimensional aspects such as a trade-off relation effectively. Our approach generates a set of melodies that maximize two fitness functions, which represent a trade-off between stability and tension. It includes a pre-defined chord progression and rhythm to initialize and evaluate population. Multi-objective genetic algorithm is applied to the music composition, it is able to successfully compose melody lines based on the chord progression.