BLUES from Music: BLind Underdetermined Extraction of Sources from Music

Michael Syskind Pedersen, Tue Lehn-Schiřler, Jan Larsen

AbstractIn this paper we propose to use an instantaneous ICA method (BLUES) to separate the instruments in a real music stereo
recording. We combine two strong separation techniques to segregate instruments from a mixture: ICA and binary
time-frequency masking. By combining the methods, we are able to make use of the fact that the sources are
differently distributed in both space, time and frequency. Our method is able to segregate an arbitrary number of
instruments and the segregated sources are maintained as stereo signals. We have evaluated our method on real stereo
recordings, and we can segregate those instruments which are spatially different from other instruments.
KeywordsICA, time frequency masking, music
TypeConference paper [With referee]
ConferenceICA2006
EditorsJustinian Rosca, Deniz Erdogmus, José C. Príncipe, Simon Haykin
Year2006    Vol. 3889    pp. 392-399
PublisherSpringer Berlin / Heidelberg
SeriesLecture Notes in Computer Science
ISBN / ISSNISBN 3-540-32630-8
Electronic version(s)[pdf]
Publication linkhttp://www.springerlink.com/(m33ypy45gn3y4p45voyskg55)/app/home/contribution.asp?referrer=parent&backto=issue,49,120;journal,10,3313;linkingpublicationresults,1:105633,1
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing


Back  ::  IMM Publications