The influence of the rhythm with the pitch on melodic segmentation

Abstract

Music segmentation is an important issue for musical analysis in that it provides an overview of the internal structure of a composition. This paper presents a novel algorithm that discovers musical segments in symbolic musical data. The proposed algorithm considers simultaneously the two fundamental components of music, i.e. melody and rhythm and it uses the principles belonging to the information theory in order to identify melodic cells. The algorithm is tested against a small manually-annotated dataset of musical excerpts and results are analysed; it is shown that the technique is promising.