04/06/2006: New features to generate a harmonic playlist and to synchronize the playlist with a mp3 player in 0.9.6. Also many fixes and additions.

02/22/2006: New function to share audio features and rate songs via a webservice in 0.9.5. Also many fixes and additions.

11/23/2005: Minor release 0.9.1 fixing music playing under Windows.

11/09/2005: Mailing lists are finally fixed.

08/15/2005: Added partly untested tutorial for compiling MusicMiner on Max OS X contributed by Christopher Suckling.

07/29/2005: MusicMiner 0.8.4: Better audio processing with MPlayer, including support for *.wma and *.m4a formats.

07/22/2005: Please report bugs in the tracker and ask for help in the forums until the mailing lists are fixed.

07/20/2005: MusicMiner 0.8.3: Fixes database startup problem reported on some systems.

07/14/2005: MusicMiner 0.8.2: Fixes problem with spaces in install path.

07/13/2005: MusicMiner 0.8.1: Fixes several issues.

07/09/2005: MusicMiner 0.8.0 released!

Databionic MusicMiner

The Databionic MusicMiner is a browser for music based on data mining techniques. You can create MusicMaps to visualize the similarity of songs and artists. Explore your music and create playlists based on the paradigm of geographical maps! Features include:

  • Automatic parsing of a folder tree with music files (MP3, OGG, WMA, M4A, MP2, WAV).
  • Automatic description of digital audio files by sound.
  • Creation of MusicMaps to navigate the sound space based on the paradigm of geographical maps.
  • Visual creation of playlists.
  • Similarity search in music collection based on sound.
  • Customizable hierarchichal browsing of the database by e.g. genre/artist/album or year/artist.
  • Flexible database including the seperate storage of several artists per song, albums and playlists as part of a playlist.
  • Import and export of meta information based on XML.


MusicMiner was presented among other places at the Cebit 2005 in Hannover, Germany and is described in many articles. It is being developed as part of a research project of the Databionics Research Group at the University of Marburg, Germany. It heavily relies on the functionality of the Databionic ESOM Tools. The MusicMiner is written in Java for maximum portability and published under the terms of the GPL.

Please understand that our main focus is on research and teaching. We can only provide limited user support via the mailing lists. We welcome everybody to participate and further develop the tools. The best way to start is to join the mailing lists and tell us about your plans. See the jobs page for tasks where you could help.

If you use MusicMiner in your scientific work, please cite the one of the following references:

Moerchen, F., Ultsch, A., Thies, M., Loehken, I.: Modelling timbre distance with temporal statistics from polyphonic music, IEEE Transactions on Speech and Audio Processing, 14(1), pp. 81-90, (2006)
Moerchen, F., Ultsch, Noecker, M., Stamm, C.: Databionic visualization of music collections according to perceptual distance, Proceedings 6th International Conference on Music Information Retrieval (ISMIR 2005), London, UK, pp. 396-403
Moerchen, F., Ultsch, A., Thies, M., Loehken, I., Noecker, M., Stamm, C., Efthymiou, N., Kuemmerer. M.: MusicMiner: Visualizing perceptual distances of music as topograpical maps, Technical Report Dept. of Mathematics and Computer Science, University of Marburg, Germany, (2005)