Visual mining in music collections with Emergent SOM

Abstract

Different methods of organizing large collections of music with databionic mining techniques are described. The Emergent Self-Organizing Map is used to cluster and visualize similar artists and songs. The first method is the MusicMiner system that utilizes semantic descriptions learned from low level audio features for each song. The second method uses tags that have been assigned to music artists by the users of the social music platform Last.fm. For both methods we demonstrate the visualization capabilities of the U-Map. An intuitive browsing of large music collections is offered based on the paradigm of topographic maps. The semantic concepts behind the features enhance the interpretability of the maps.