Looking into the minds of Bach, Haydn and Beethoven: Classification and generation of composer-specific music
|Title||Looking into the minds of Bach, Haydn and Beethoven: Classification and generation of composer-specific music|
|Year of Publication||2014|
|Authors||Herremans D., Martens D, Sörensen K.|
|Institution||University of Antwerp, Faculty of Applied Economics|
|Type||Technical Report 2014:001- UA, Faculty of Applied Economics|
|Keywords||Classification, Computer Aided Composition, Metaheuristics, Variable Neighborhood Search (VNS)|
In this paper a number of musical features are extracted from a large music database, which are consequently used to build three composer classification models. The first two models, an if-then ruleset and a decision tree, result in an understanding of the style differences between Bach, Haydn and Beethoven. The third model, a logistic regression model, gives the probability that a piece is composed by a certain composer. This model is integrated in the objective function of a previously developed variable neighborhood search algorithm that can generate counterpoint. The result is a system that can generate an endless stream of counterpoint music with composer-specific characteristics that sounds pleasing to the ear. This system is implemented as an Android app called FuX that can be installed on any Android phone or tablet.