Genre-oriented Organization of Music Collections Using the SOMeJB System : An Analysis of Rhythm Patterns and Other Features

With the advent of larger electronic music repositories, the automatic organization of music into different genre categories is receiving increased attention. The creation of such genre hierarchies, as well as ways for providing useful interfaces to these, poses an interesting challenge. With the SOM-enhanced JukeBox (SOMeJB) system we developed an approach for automatically organizing pieces of music in raw audio format according to their perceived sound similarity based on Rhythm Patterns. This paper reviews the SOMeJB system and presents performance evaluations of the resulting hierarchical genre clusters. We furthermore compare the Rhythm Pattern based clustering with cluster structures obtained from other sets of features employed for genre-based music analysis. We demonstrate results based on a collection of about 24 hours of music.

[1]  B. Feiten,et al.  Automatic indexing of a sound database using self-organizing neural nets , 1994 .

[2]  Elias Pampalk,et al.  Please Scroll down for Article Journal of New Music Research the Som-enhanced Jukebox: Organization and Visualization of Music Collections Based on Perceptual Models , 2022 .

[3]  Jonathan Foote,et al.  An overview of audio information retrieval , 1999, Multimedia Systems.

[4]  Andreas Rauber,et al.  Uncovering hierarchical structure in data using the growing hierarchical self-organizing map , 2002, Neurocomputing.

[5]  Douglas Keislar,et al.  Content-Based Classification, Search, and Retrieval of Audio , 1996, IEEE Multim..

[6]  George Tzanetakis,et al.  Musical genre classification of audio signals , 2002, IEEE Trans. Speech Audio Process..

[7]  Elias Pampalk,et al.  Content-based organization and visualization of music archives , 2002, MULTIMEDIA '02.

[8]  Hugo Fastl,et al.  Psychoacoustics: Facts and Models , 1990 .

[9]  Andreas Rauber,et al.  Text Mining in the SOMLib Digital Library System: The Representation of Topics and Genres , 2004, Applied Intelligence.

[10]  Christian Spevak,et al.  SOUNDSPOTTER – A PROTOTYPE SYSTEM FOR CONTENT-BASED AUDIO RETRIEVAL , 2002 .

[11]  E. Pampalk,et al.  Using PsychoAcoustic Models and SOMs to create a Hierarchical Structuring of Music Using PsychoAcoustic Models and Self-Organizing Maps to Create a Hierarchical Structuring of Music by Sound Similarity , 2002 .

[12]  Andreas Rauber,et al.  Automatically Analyzing and Organizing Music Archives , 2001, ECDL.