Reducing Binary Masking Artefacts in Blind Audio Source Separation
Stokes, T, Hummersone, C and Brookes, TS Reducing Binary Masking Artefacts in Blind Audio Source Separation In: AES 134th Convention, 2013-05-04 - 2013-05-07, Rome, Italy.
SRI_deposit_agreement.pdf - Accepted version Manuscript
Restricted to Repository staff only
Reducing Binary Masking Artefacts in Blind Audio Source Separation.pdf
Download (333kB) | Preview
Binary masking is a common technique for separating target audio from an interferer. Its use is often justified by the high signal-to-noise ratio achieved. The mask can introduce musical noise artefacts, limiting its perceptual performance and that of techniques that use it. Three mask-processing techniques, involving adding noise or cepstral smoothing, are tested and the processed masks are compared to the ideal binary mask using the perceptual evaluation for audio source separation (PEASS) toolkit. Each processing technique's parameters are optimised before the comparison is made. Each technique is found to improve the overall perceptual score of the separation. Results show a trade-off between interferer suppression and artefact reduction.
|Item Type:||Conference or Workshop Item (Conference Paper)|
|Divisions :||Faculty of Arts and Social Sciences > School of Arts > Sound Recording|
|Copyright Disclaimer :||© 2013 Audio Engineering Society. This convention paper has been reproduced from the author's advance manuscript without editing, corrections, or consideration by the Review Board. The AES takes no responsibility for the contents. Additional papers may be obtained by sending request and remittance to Audio Engineering Society, 60 East 42nd Street, New York, New York 10165-2520, USA; also see www.aes.org. All rights reserved. Reproduction of this paper, or any portion thereof, is not permitted without direct permission from the Journal of the Audio Engineering Society.|
|Depositing User :||Symplectic Elements|
|Date Deposited :||18 Aug 2016 15:31|
|Last Modified :||18 Aug 2016 15:31|
Actions (login required)
Downloads per month over past year