[Back]


Talks and Poster Presentations (with Proceedings-Entry):

T. Lidy, A. Rauber:
"MIREX 2005: Combined fluctuation features for music genre classification";
Poster: MIREX - Music Information Retrieval Evaluation eXchange, London, UK; 2005-09-11 - 2005-09-15; in: "MIREX 2005", (2005), 3 pages.



English abstract:
We submitted a system that uses combinations of three
feature sets (Rhythm Patterns, Statistical Spectrum Descriptor
and Rhythm Histogram) to the MIREX 2005
audio genre classification task. All feature sets are
based on fluctuation of modulation amplitudes in psychoacoustically
transformed spectrum data. For classification
we applied Support Vector Machines. Our best approach
achieved 75.27 % combined overall classification accuracy,
which is rank 5.


Electronic version of the publication:
http://publik.tuwien.ac.at/files/pub-inf_3610.pdf


Created from the Publication Database of the Vienna University of Technology.