PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Learning and clean-up in a large scale music database
Lars Kai Hansen, Tue Lehn-Schiøler, T Petersen, J Arenas-Garcia, Jan Larsen and S Jensen
ICASSP 2007 2006.

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.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
Information Retrieval & Textual Information Access
ID Code:2814
Deposited By:Tue Lehn-Schiøler
Deposited On:22 November 2006