We are experiencing a tremendous increase in the amount of music being made
available in digital form. With the creation of large multimedia collections,
however, we need to devise ways to make those collections accessible to the
users. While music repositories exist today, they mostly limit access to
their content to query-based retrieval of their items based on textual
meta-information, with some advanced systems supporting acoustic queries.
What we would like to have additionally, is a way to facilitate exploration
of musical libraries. We thus need to automatically organize music according
to its sound characteristics in such a way that we find similar pieces of
music grouped together, allowing us to find a classical section, or a
hard-rock section etc. in a music repository.
The SOMeJB Music Digital Library Project aims at creating such a browsable music archive by combining a variety of technologies from the fields of audio processing, neural networks, and information visualization, to create maps of music archives. It has its roots in the SOMLib Digital Library for text archives. It is based on the self-organizing map (SOM), a popular unsupervised neural network, and its extension, the Growing Hierarchical Self-Organizing Map (GHSOM), used to organize pieces of music available as, e.g., mp3 files, according to their musical sound characteristics, i.e. creating a kind of genre-based organization. The resulting maps of the music archive can be explored, and new, unknown pieces of music similar to ones personal likings can be discovered, with Islands of Music and Weather Charts providing an intuitive interface to the system.
Overview
Architecture
An overview of the architecture of the SOMeJB system,
describing the various modules and methods developed, starting from
the Feature extraction process, via the psychoacoustic preprocessing employed, to SOM-based clustering and the Islands of Music visualization.
Experiments
Description of the various experiments as well as on-line
demonstrations of the SOMeJB system using different data sets, including links to down-sampled mp3-files allowing interactive exploration and browsing of our music archives. (Please note: due to copyright-reasons we do NOT provide full MP3-files of titles, but rather segments of a few seconds length, down-sampled to phone-line quality. Still, the provided audio files allow you to listen to parts of the titles, analyze their characteristics, and thus evaluate the performance of our system.)
Publications
A list of some selected publications relating to the
SOMeJB project.
Related Projects / Sub-Projects
A number of sub-projects that are related to or form a major part of the SOMeJB project. Here we provide links to the according home-pages.
Download
The source code of some of the tools we use for creating a SOM-enhanced Jukebox, as well as some brief descriptions, are now available for you to download, and to play around with, and more are there to come. (they come, however, without any warranty...)
Feedback
If you have questions or want to provide feedback on any aspect
of the SOMeJB music digital library system, please send an e-mail to
rauber@ifs.tuwien.ac.at