Learning and clean-up in a large scale music database

Lars Kai Hansen, Tue Lehn-Schiøler, Kaare Brandt Petersen, Jeronimo Arenas-Garcia, Jan Larsen, Søren Holdt Jensen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearch

    197 Downloads (Pure)

    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.
    Original languageEnglish
    Title of host publicationEUSIPCO 2007
    Publication date2007
    Publication statusPublished - 2007
    EventEUSIPCO 2007 -
    Duration: 1 Jan 2007 → …

    Conference

    ConferenceEUSIPCO 2007
    Period01/01/2007 → …

    Keywords

    • Databases
    • Multimedia databases

    Fingerprint Dive into the research topics of 'Learning and clean-up in a large scale music database'. Together they form a unique fingerprint.

    Cite this