Publikationsansicht

BLUES from Music: Blind Underdetermined Extraction of Sources from (2006)

Abstract
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. 1

Details der Publikation
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.1222
Quelle http://www2.imm.dtu.dk/pubdb/views/edoc_download.php/4060/pdf/imm4060.pdf
Mitarbeiter CiteSeerX
Archiv CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Typ text
Sprache Englisch
Verknüpfungen 10.1.1.107.3613, 10.1.1.40.3477, 10.1.1.6.6960, 10.1.1.22.5314, 10.1.1.9.8254, 10.1.1.124.298, 10.1.1.35.4016, 10.1.1.19.6930, 10.1.1.84.298, 10.1.1.91.5988, 10.1.1.118.4375, 10.1.1.139.5510, 10.1.1.121.3499, 10.1.1.68.4632, 10.1.1.118.66, 10.1.1.87.8649