The SOM-enhanced JukeBox:
   Organization and Visualization of Music Collections based on Perceptual Models


Andreas Rauber                  Elias Pampalk                     Dieter Merkl 
Dept. of Software Technology    Austrian Research Institute for   Dept. of Software Technology
Vienna Univ. of Technology      Artificial Intelligence (OeFAI)   Vienna Univ. of Technology
A-1040 Vienna, Austria          A-1010 Vienna, Austria            A-1040 Vienna, Austria
andi@ifs.tuwien.ac.at           elias@oefai.at                    dieter@ifs.tuwien.ac.at


Abstract:
The availability of large music repositories calls for new ways of automatically organizing 
and accessing them. While artist-based listings or title indexes may help in locating a specific 
piece of music, a more intuitive, genre-based organization is required to allow users to browse 
an archive and explore its contents. So far, however, these organizations following musical 
styles have to be designed manually.

With the SOM-enhanced JukeBox (SOMeJB) we propose an approach to automatically create an 
organization of music archives following their perceived sound similarity. More specifically, 
characteristics of frequency spectra are extracted and transformed according to psychoacoustic 
models. The resulting psychoacoustic Rhythm Patterns are further organized using the 
Growing Hierarchical Self-Organizing Map, an unsupervised neural network. On top of this 
advanced visualizations including Islands of Music (IoM) and Weather Charts offer an interface 
for interactive exploration of large music repositories.

Keywords: Music Clustering, Rhythm Patterns, Self-Organizing Map (SOM), Interfaces


-----
In:
Journal of New Music Research, (JNMR), Swets and Zeitlinger, 32(2):193-210, 2003.
on-line digital library of Swets&Zeitlinger: 
http://www.extenza-eps.com/extenza/loadHTML?objectIDValue=16745&type=abstract

Project Website: http://www.ifs.tuwien.ac.at/~andi/somejb