University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Discriminative Enhancement for Single Channel Audio Source Separation using Deep Neural Networks

Grais, EM, Roma, G, Simpson, AJR and Plumbley, MD (2016) Discriminative Enhancement for Single Channel Audio Source Separation using Deep Neural Networks arXiv.

Full text not available from this repository.

Abstract

The sources separated by most single channel audio source separation techniques are usually distorted and each separated source contains residual signals from the other sources. To tackle this problem, we propose to enhance the separated sources by decreasing the distortion and interference between the separated sources using deep neural networks (DNNs). Two different DNNs are used in this work. The first DNN is used to separate the sources from the mixed signal. The second DNN is used to enhance the ...

Item Type: Article
Authors :
NameEmailORCID
Grais, EMUNSPECIFIEDUNSPECIFIED
Roma, Gg.roma@surrey.ac.ukUNSPECIFIED
Simpson, AJRUNSPECIFIEDUNSPECIFIED
Plumbley, MDm.plumbley@surrey.ac.ukUNSPECIFIED
Date : 16 September 2016
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 13:54
Last Modified : 03 Oct 2017 06:06
URI: http://epubs.surrey.ac.uk/id/eprint/840749

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800