Genetic art is a recent art form generated by computers based on the genetic algorithms (GAs). In this paper, the components of a GA embedded into a genetic art tool named AMUSE are introduced. AMUSE is used to generate improvised melodies over a musical piece given a harmonic context. Population of melodies is evolved towards a
musical form based on a fitness function that evaluates ten different melodic and rhythmic features. Performance analysis of the GA based on a public evaluation shows that the objectives used by the fitness function are assembled properly and it is a successful artificial intelligence application.
Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten