Music Similarity Estimation with the Mean-Covariance Restricted Boltzmann Machine

J. Schluter, C. Osendorfer
2011 2011 10th International Conference on Machine Learning and Applications and Workshops  
Existing content-based music similarity estimation methods largely build on complex hand-crafted feature extractors, which are difficult to engineer. As an alternative, unsupervised machine learning allows to learn features empirically from data. We train a recently proposed model, the mean-covariance Restricted Boltzmann Machine [1], on music spectrogram excerpts and employ it for music similarity estimation. In k-NN based genre retrieval experiments on three datasets, it clearly outperforms
more » ... CC-based methods, beats simple unsupervised feature extraction using k-Means and comes close to the stateof-the-art. This shows that unsupervised feature extraction poses a viable alternative to engineered features.
doi:10.1109/icmla.2011.102 dblp:conf/icmla/SchluterO11 fatcat:yftfkxqnjbchzpae7t3j3d4fi4