Towards effective singing voice extraction from stereophonic recordings
Towards effective singing voice extraction from stereophonic recordings
Extracting a singing voice from its music accompaniment can significantly facilitate certain applications of Music Information Retrieval including singer identification and singing melody extraction. In this paper, we present a hybrid approach for this purpose, which combines properties of the Azimuth Discrimination and Resynthesis (ADRess) method with Independent Component Analysis (ICA). Our proposed approach is developed specifically for the case of singing voice separation from stereophonic recordings. The paper presents the characteristics of the proposed method and details an objective evaluation of its effectiveness.
9781424442959
233-236
Sofianos, S.
815ee3cd-92b0-4975-a312-6ca783dc2e6b
Ariyaeeinia, A.
b002316a-7016-4302-9821-c95782daecc4
Polfreman, R.
26424c3d-b750-4868-bf6e-2bbb3990df84
28 June 2010
Sofianos, S.
815ee3cd-92b0-4975-a312-6ca783dc2e6b
Ariyaeeinia, A.
b002316a-7016-4302-9821-c95782daecc4
Polfreman, R.
26424c3d-b750-4868-bf6e-2bbb3990df84
Sofianos, S., Ariyaeeinia, A. and Polfreman, R.
(2010)
Towards effective singing voice extraction from stereophonic recordings.
In 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP).
IEEE.
.
(doi:10.1109/ICASSP.2010.5496004).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Extracting a singing voice from its music accompaniment can significantly facilitate certain applications of Music Information Retrieval including singer identification and singing melody extraction. In this paper, we present a hybrid approach for this purpose, which combines properties of the Azimuth Discrimination and Resynthesis (ADRess) method with Independent Component Analysis (ICA). Our proposed approach is developed specifically for the case of singing voice separation from stereophonic recordings. The paper presents the characteristics of the proposed method and details an objective evaluation of its effectiveness.
This record has no associated files available for download.
More information
Published date: 28 June 2010
Additional Information:
ISSN: 1520-6149
Venue - Dates:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Dallas, United States, 2010-06-28
Identifiers
Local EPrints ID: 181931
URI: http://eprints.soton.ac.uk/id/eprint/181931
ISBN: 9781424442959
PURE UUID: 84f9c770-2df1-47e1-81cc-f12124783548
Catalogue record
Date deposited: 26 Apr 2011 10:25
Last modified: 14 Mar 2024 02:58
Export record
Altmetrics
Contributors
Author:
S. Sofianos
Author:
A. 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