User-guided system to generate spanish popular music

Abstract

The automatic generation of music is an emerging field of research that has attracted wide attention in Computer Science. Additionally, the interaction between users and machines is nowadays very present in our daily lives, and influences fields such as Economy, Sports or Arts. Following this approach, this work develops an intelligent system that generates melodies based on Spanish popular music and some indications of the users through an interface. The system creates a melody by learning from the corpus selected through a Markov model, which is also influenced by the users’ preferences. Several experiments were carried out to evaluate the musical quality and the usefulness of the system to interact with the user and generate music. The results of the evaluation shows that the proposal is able to generate music adapted to the style standards of Spanish popular music and to the users’ indications.