DMCA
AN OVERVIEW OF INFORMED AUDIO SOURCE SEPARATION
| Citations: | 2 - 1 self |
BibTeX
@MISC{Liutkus_anoverview,
author = {Antoine Liutkus and Jean-louis Durrieu and Laurent Daudet and Gaël Richard},
title = {AN OVERVIEW OF INFORMED AUDIO SOURCE SEPARATION},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Audio source separation consists in recovering different un-known signals called sources by filtering their observed mix-tures. In music processing, most mixtures are stereophonic songs and the sources are the individual signals played by the instruments, e.g. bass, vocals, guitar, etc. Source separation is often achieved through a classical generalized Wiener fil-tering, which is controlled by parameters such as the power spectrograms and the spatial locations of the sources. For an efficient filtering, those parameters need to be available and their estimation is the main challenge faced by separa-tion algorithms. In the blind scenario, only the mixtures are available and performance strongly depends on the mixtures considered. In recent years, much research has focused on informed separation, which consists in using additional avail-able information about the sources to improve the separation quality. In this paper, we review some recent trends in this direction. 1.
Keyphrases
overview informed audio source separation separa-tion algorithm audio source separation stereophonic song main challenge classical generalized wiener fil-tering additional avail-able information efficient filtering observed mix-tures informed separation recent year separation quality much research recent trend individual signal blind scenario source separation power spectrogram spatial location music processing different un-known signal
