Classifying Music by Genre Using the Wavelet Packet Transform and a Round-robin Ensemble

The vast amount of music available electronically presents considerable challenges for information retrieval. There is a need to annotate music items with descriptors in order to facilitate retrieval. In this paper we present a process for determining the music genre of an item using the Discrete Wavelet Transform and a round-robin classification technique. The wavelet transform is used to extract time and frequency features that are used to classify items by genre. Rather than use a single multi-class classifier we use an ensemble of binary classifiers with each classifier trained on a pair of genres. Our evaluation shows that this approach achieves very high classification accuracy.