Abstract | ||
---|---|---|
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, on music spectrogram excerpts and employ it for music similarity estimation. In k-NN based genre retrieval experiments on three datasets, it clearly outperforms MFCC-based methods, beats simple unsupervised feature extraction using k-Means and comes close to the state-of-the-art. This shows that unsupervised feature extraction poses a viable alternative to engineered features. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICMLA.2011.102 | ICMLA), 2011 10th International Conference |
Keywords | DocType | Volume |
Boltzmann machines,content-based retrieval,feature extraction,learning (artificial intelligence),music,pattern classification,MFCC based methods,complex hand crafted feature extractors,content based music similarity estimation,k-NN based genre retrieval experiments,k-means,mean covariance restricted boltzmann machine,music spectrogram excerpts,unsupervised feature extraction,unsupervised machine learning,MIR,mcRBM,music similarity,unsupervised feature extraction | Conference | 2 |
ISBN | Citations | PageRank |
978-1-4577-2134-2 | 20 | 1.13 |
References | Authors | |
21 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jan Schlüter | 1 | 231 | 18.45 |
Christian Osendorfer | 2 | 21 | 2.15 |