PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

BLUES from Music: BLind Underdetermined Extraction of Sources from Music
Michael S. Pedersen, T. Lehn-Schiøler and Jan Larsen
In: ICA 2006(2005).


Abstract. In 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 instruments which are spatially different from other instruments.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
ID Code:1893
Deposited By:Michael Pedersen
Deposited On:29 December 2005