University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network

Simpson, AR, Roma, G and Plumbley, M (2015) Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network In: Latent Variable Analysis and Signal Separation: 12th International Conference, LVA/ICA 2015, 25-28 Aug 2015, Liberec, Czech Republic.

[img] Text
SimpsonRomaPlumbley15-lva_accepted.pdf - Accepted version Manuscript
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (220kB)
[img]
Preview
Text
1504.04658v1.pdf
Available under License : See the attached licence file.

Download (528kB) | Preview
[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

Identification and extraction of singing voice from within musical mixtures is a key challenge in source separation and machine audition. Recently, deep neural networks (DNN) have been used to estimate 'ideal' binary masks for carefully controlled cocktail party speech separation problems. However, it is not yet known whether these methods are capable of generalizing to the discrimination of voice and non-voice in the context of musical mixtures. Here, we trained a convolutional DNN (of around a billion parameters) to provide probabilistic estimates of the ideal binary mask for separation of vocal sounds from real-world musical mixtures. We contrast our DNN results with more traditional linear methods. Our approach may be useful for automatic removal of vocal sounds from musical mixtures for 'karaoke' type applications.

Item Type: Conference or Workshop Item (Conference Paper)
Subjects : Signal processing
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
AuthorsEmailORCID
Simpson, ARUNSPECIFIEDUNSPECIFIED
Roma, GUNSPECIFIEDUNSPECIFIED
Plumbley, MUNSPECIFIEDUNSPECIFIED
Date : 15 August 2015
Identification Number : 10.1007/978-3-319-22482-4_50
Contributors :
ContributionNameEmailORCID
EditorVincent, EUNSPECIFIEDUNSPECIFIED
EditorYeredor, AUNSPECIFIEDUNSPECIFIED
EditorKoldovský, ZUNSPECIFIEDUNSPECIFIED
EditorTichavský, PUNSPECIFIEDUNSPECIFIED
PublisherSpringer International Publishing, UNSPECIFIEDUNSPECIFIED
Uncontrolled Keywords : Deep learning, Supervised learning, Convolution, Source separation
Related URLs :
Additional Information : The original publication is available at http://link.springer.com/chapter/10.1007/978-3-319-22482-4_50
Depositing User : Symplectic Elements
Date Deposited : 02 Feb 2016 09:01
Last Modified : 02 Feb 2016 09:01
URI: http://epubs.surrey.ac.uk/id/eprint/809734

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