Singing Voice Separation Based On Non-vocal Independent Component Subtraction and Amplitude Discrimination
Singing Voice Separation Based On Non-vocal Independent Component Subtraction and Amplitude Discrimination
Many applications of Music Information Retrieval can benefit from effective isolation of the music sources. Earlier work by the authors led to the development of a system that is based on Azimuth Discrimination and Resynthesis (ADRess) and can extract the singing voice from reverberant stereophonic mixtures. We propose an extension to our previous method that is not based on ADRess and exploits both channels of the stereo mix more effectively. For the evaluation of the system we use a dataset that contains songs convolved during mastering as well as the mixing process (i.e. “real-world” conditions). The metrics for objective evaluation are based on bss_eval.
9783200019409
DAFX-1
Institute of Electronic Music and Acoustics
Sofianos, Stratis
ad0612ce-cade-4ffe-be7b-9377ef9471cc
Ariyaeeinia, Aladdin
49029cf8-701f-4170-a564-0d0e5e7c5574
Polfreman, Richard
26424c3d-b750-4868-bf6e-2bbb3990df84
6 September 2010
Sofianos, Stratis
ad0612ce-cade-4ffe-be7b-9377ef9471cc
Ariyaeeinia, Aladdin
49029cf8-701f-4170-a564-0d0e5e7c5574
Polfreman, Richard
26424c3d-b750-4868-bf6e-2bbb3990df84
Sofianos, Stratis, Ariyaeeinia, Aladdin and Polfreman, Richard
(2010)
Singing Voice Separation Based On Non-vocal Independent Component Subtraction and Amplitude Discrimination.
In Proceedings of the 13th International Conference on Digital Audio Effects (DAFx-10).
Institute of Electronic Music and Acoustics.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Many applications of Music Information Retrieval can benefit from effective isolation of the music sources. Earlier work by the authors led to the development of a system that is based on Azimuth Discrimination and Resynthesis (ADRess) and can extract the singing voice from reverberant stereophonic mixtures. We propose an extension to our previous method that is not based on ADRess and exploits both channels of the stereo mix more effectively. For the evaluation of the system we use a dataset that contains songs convolved during mastering as well as the mixing process (i.e. “real-world” conditions). The metrics for objective evaluation are based on bss_eval.
Text
SofianosAriyaeeiniaPolfreman_DAFx10_P8.pdf
- Version of Record
Restricted to Repository staff only
Request a copy
More information
Published date: 6 September 2010
Venue - Dates:
13th IInternational Conference on Digital Audio Effects (DAFx-10), Graz, Austria, 2010-09-06
Identifiers
Local EPrints ID: 181941
URI: http://eprints.soton.ac.uk/id/eprint/181941
ISBN: 9783200019409
PURE UUID: 8bac27db-4429-409f-8f9c-477b9410fe4f
Catalogue record
Date deposited: 27 Apr 2011 14:38
Last modified: 14 Mar 2024 02:58
Export record
Contributors
Author:
Stratis Sofianos
Author:
Aladdin Ariyaeeinia
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics