Document Type
Article
Language
eng
Format of Original
8 p.
Publication Date
6-2013
Publisher
Institute of Engineering and Technology
Source Publication
IET Signal Processing
Source ISSN
1751-9683
Original Item ID
doi: 10.1049/iet-spr.2012.0167
Abstract
In this study, the authors propose multichannel weighted Euclidean (WE) and weighted cosh (WCOSH) cost function estimators for speech enhancement in the distributed microphone scenario. The goal of the work is to illustrate the advantages of utilising additional microphones and modified cost functions for improving signal-to-noise ratio (SNR) and segmental SNR (SSNR) along with log-likelihood ratio (LLR) and perceptual evaluation of speech quality (PESQ) objective metrics over the corresponding single-channel baseline estimators. As with their single-channel counterparts, the perceptually-motivated multichannel WE and WCOSH estimators are functions of a weighting law parameter, which influences attention of the noisy spectral amplitude through a spectral gain function, emphasises spectral peak (formant) information, and accounts for auditory masking effects. Based on the simulation results, the multichannel WE and WCOSH cost function estimators produced gains in SSNR improvement, LLR output and PESQ output over the single-channel baseline results and unweighted cost functions with the best improvements occurring with negative values of the weighting law parameter across all input SNR levels and noise types.
Recommended Citation
Trawicki, Marek B. and Johnson, Michael T., "Distributed Multichannel Speech Enhancement Based on Perceptually-Motivated Bayesian Estimators of the Spectral Amplitude" (2013). Electrical and Computer Engineering Faculty Research and Publications. 50.
https://epublications.marquette.edu/electric_fac/50
ADA Accessible Version
Comments
Accepted version. IET Signal Processing, Vol. 7, No. 4 (June 2013): 337-344. DOI. © 2013 The Institute of Electrical and Electronics Engineers. Used with permission.