%0 Conference Paper %B 13th International Society for Music Information Retrieval Conference %D 2012 %T Learnng Sparse Feature Representations For Music Annotation And Retrieval %A Juhan Nam %A Jorge Herrera %A Slaney, Malcolm %A Smith, Julius %C Porto, Portugal %U http://ccrma.stanford.edu/~juhan/pubs/jnam-ismir2012.pdf %X We present a data-processing pipeline based on sparse feature learning and describe its applications to music annotation and retrieval. Content-based music annotation and retrieval systems process audio starting with features. While commonly used features, such as MFCC, are handcrafted to extract characteristics of the audio in a succinct way, there is increasing interest in learning features automatically from data using unsupervised algorithms. We describe a systemic approach applying feature-learning algorithms to music data, in particular, focusing on a highdimensional sparse-feature representation. Our experiments show that, using only a linear classifier, the newly learned features produce results on the CAL500 dataset comparable to state-of-the-art music annotation and retrieval systems.  %Z   %8 10/2012