Search for sounds - a machine learning approach

Jan Larsen

AbstractSearch is a “productivity engine” simply important to enhancing quality of life in general. We present a machine leaning framework which is essential for sound search and organization based on musical features, meta data, and social network information. Two music information processing tasks: genre classification and independent component analysis for music separation are discussed in detail.
Keywordssearch sound audio machine learning ica
TypeMisc [Presentation]
Year2006    Month March
PublisherInformatics and Mathematical Modelling
AddressRichard Petersens Plads, Building 321, DK-2800 Kgs. Lyngby, Denmark
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing


Back  ::  IMM Publications