A comparison of statistical approaches to symbolic genre recognition
Carlos Pérez-Sancho, Pedro J. Ponce de León and José Iñesta
Proceedings of the 2006 International Computer Music Conference
International Computer Music Association
ISBN 0 9713192 4 3
Previous work in genre recognition and characterization from symbolic sources (melodies extracted from MIDI files) carried out by our group pointed our research to study how the different utilized approaches perform and how their different abilities can be used together in order to improve both the accuracy and robustness of their decisions. Results for a corpus of Jazz and Classical music pieces are presented and discussed.