Reducing Binary Masking Artifacts in Blind Audio Source Separation
×
Cite This
Citation & Abstract
T. Stokes, C. Hummersone, and T. Brookes, "Reducing Binary Masking Artifacts in Blind Audio Source Separation," Paper 8853, (2013 May.). doi:
T. Stokes, C. Hummersone, and T. Brookes, "Reducing Binary Masking Artifacts in Blind Audio Source Separation," Paper 8853, (2013 May.). doi:
Abstract: 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 artifacts, 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 optimized 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 artifact reduction.
@article{stokes2013reducing,
author={stokes, toby and hummersone, christopher and brookes, tim},
journal={journal of the audio engineering society},
title={reducing binary masking artifacts in blind audio source separation},
year={2013},
volume={},
number={},
pages={},
doi={},
month={may},}
@article{stokes2013reducing,
author={stokes, toby and hummersone, christopher and brookes, tim},
journal={journal of the audio engineering society},
title={reducing binary masking artifacts in blind audio source separation},
year={2013},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={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 artifacts, 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 optimized 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 artifact reduction.},}
TY - paper
TI - Reducing Binary Masking Artifacts in Blind Audio Source Separation
SP -
EP -
AU - Stokes, Toby
AU - Hummersone, Christopher
AU - Brookes, Tim
PY - 2013
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2013
TY - paper
TI - Reducing Binary Masking Artifacts in Blind Audio Source Separation
SP -
EP -
AU - Stokes, Toby
AU - Hummersone, Christopher
AU - Brookes, Tim
PY - 2013
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2013
AB - 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 artifacts, 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 optimized 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 artifact reduction.
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 artifacts, 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 optimized 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 artifact reduction.
Authors:
Stokes, Toby; Hummersone, Christopher; Brookes, Tim
Affiliation:
University of Surrey, Guildford, Surrey, UK
AES Convention:
134 (May 2013)
Paper Number:
8853
Publication Date:
May 4, 2013Import into BibTeX
Subject:
Audio Processing and Semantics
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=16754