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

Grais, Emad M, Roma, G, Simpson, AJR and Plumbley, Mark (2017) Discriminative Enhancement for Single Channel Audio Source Separation using Deep Neural Networks In: 13th International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2017), 2017-02-21 - 2017-02-23, Grenoble, France.

Preview	Text final_lva_ica2017.pdf - Accepted version Manuscript Available under License : See the attached licence file. Download (223kB) | Preview
Preview	Text (licence) SRI_deposit_agreement.pdf Available under License : See the attached licence file. Download (33kB) | Preview

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 to decrease 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 separated signals. To consider the interactions between the separated sources, we propose to use a single DNN to enhance all the separated sources together. To reduce the residual signals of one source from the other separated sources (interference), we train the DNN for enhancement discriminatively to maximize the dissimilarity between the predicted sources. The experimental results show that using discriminative enhancement decreases the distortion and interference between the separated sources

Item Type:	Conference or Workshop Item (Conference Paper)
Subjects :	Electronic Engineering
Divisions :	Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :	Name Email ORCID Grais, Emad M grais@surrey.ac.uk Roma, G Simpson, AJR Plumbley, Mark m.plumbley@surrey.ac.uk
Date :	15 February 2017
Identification Number :	10.1007/978-3-319-53547-0_23
Copyright Disclaimer :	The final publication is available at link.springer.com
Contributors :	Contribution Name Email ORCID Springer,
Related URLs :	Publisher
Additional Information :	Part of the Lecture Notes in Computer Science book series (LNCS, volume 10169)
Depositing User :	Symplectic Elements
Date Deposited :	14 Dec 2016 15:09
Last Modified :	16 Mar 2018 10:44
URI:	http://epubs.surrey.ac.uk/id/eprint/813112

Actions (login required)

View Item

Downloads