Citation

BibTex format

@inproceedings{Lightburn:2017:10.1109/ICASSP.2017.7952238,
author = {Lightburn, L and De, Sena E and Moore, AH and Naylor, PA and Brookes, D},
doi = {10.1109/ICASSP.2017.7952238},
pages = {661--665},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
title = {Improving the perceptual quality of ideal binary masked speech},
url = {http://dx.doi.org/10.1109/ICASSP.2017.7952238},
year = {2017}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - It is known that applying a time-frequency binary mask to very noisy speech can improve its intelligibility but results in poor perceptual quality. In this paper we propose a new approach to applying a binary mask that combines the intelligibility gains of conventional binary masking with the perceptual quality gains of a classical speech enhancer. The binary mask is not applied directly as a time-frequency gain as in most previous studies. Instead, the mask is used to supply prior information to a classical speech enhancer about the probability of speech presence in different time-frequency regions. Using an oracle ideal binary mask, we show that the proposed method results in a higher predicted quality than other methods of applying a binary mask whilst preserving the improvements in predicted intelligibility.
AU - Lightburn,L
AU - De,Sena E
AU - Moore,AH
AU - Naylor,PA
AU - Brookes,D
DO - 10.1109/ICASSP.2017.7952238
EP - 665
PB - Institute of Electrical and Electronics Engineers (IEEE)
PY - 2017///
SN - 1520-6149
SP - 661
TI - Improving the perceptual quality of ideal binary masked speech
UR - http://dx.doi.org/10.1109/ICASSP.2017.7952238
UR - http://hdl.handle.net/10044/1/45037
ER -

Contact

For more information about the group, please contact:

Dr Dan Goodman
+44 (0)20 7594 6264
d.goodman@imperial.ac.uk