@CONFERENCE\{IMM2007-04860, author = "L. K. Hansen and T. Lehn-Schi{\o}ler and K. B. Petersen and J. Arenas-Garcia and J. Larsen and S. H. Jensen", title = "Learning and clean-up in a large scale music database", year = "2007", keywords = "Databases, Multimedia databases", booktitle = "{EUSIPCO} 2007", volume = "", series = "", editor = "", publisher = "", organization = "", address = "", url = "http://www2.compute.dtu.dk/pubdb/pubs/4860-full.html", abstract = "We have collected a database of musical features from radio broadcasts (N > 100.000). The database poses a number of hard modeling challenges including: Segmentation problems and missing metadata. We describe our efforts towards cleaning the database using signal processing and machine learning tools." }