Music Segmentation With Genetic Algorithms

Brigitte Rafael, Stefan Oertl, Michael Affenzeller, Stefan Wagner

Abstract: Music segmentation is a key issue in music information retrieval (MIR) as it provides an insight into the structure of a composition. Based on structural information, several tasks related to MIR such as searching and browsing large music collections, visualizing musical structure, lyric alignment, and music summarization can be further improved.Various approaches are available to achieve an appropriate segmentation of a given composition. The authors of this paper present an approach to apply genetic algorithms for a solution to the segmentation problem.