Spectral Subtraction With Variance Reduced Noise Spectrum Estimates

There are no files associated with this record.

Title Spectral Subtraction With Variance Reduced Noise Spectrum Estimates
Author Wojcicki, Kamil; Shannon, Ben James; Paliwal, Kuldip Kumar
Publication Title Proceedings of the 11th Australasian International Conference on Speech Science and Technoligy
Editor Paul Warren and Catherine I. Watson
Year Published 2006
Place of publication Canberra City, ACT
Publisher ASSTA
Abstract Spectral subtraction has the drawback that it introduces an unpleasant residual noise. This noise is a result of under-subtraction which occurs due to high variance of noise magnitude spectrum estimates. In this study we investigate a number of smoothing techniques that can be employed to reduce this variability. We extend the scope of this paper by using the phase spectrum in a novel manner along with the processed magnitude spectrum. This is based on recent findings which suggest that estimation of the phase spectrum using low dynamic range analysis windows (at 20–40ms window durations) is beneficial for speech enhancement. Using an objective speech quality measure and spectrogram analysis we show that the smoothing of noise magnitude spectrum estimates is an effective method of suppressing musical noise. We also show that the use of a low dynamic range analysis window for estimation of the phase spectrum of noisy speech results in a reduction of background noise. However, we found that combining the two techniques offers no advantage over spectral subtraction alone.
Peer Reviewed Yes
Published Yes
Publisher URI http://www.assta.org/?q=sst-2006
Conference name Eleventh Australasian International Conference on Speech Science and Technology
Location Auckland, New Zealand
Date From 2006-12-06
Date To 2006-12-08
URI http://hdl.handle.net/10072/13319
Date Accessioned 2007-03-18
Date Available 2011-05-06T06:45:23Z
Language en_AU
Research Centre Institute for Integrated and Intelligent Systems
Faculty Faculty of Science, Environment, Engineering and Technology
Subject PRE2009-Speech Recognition
Publication Type Conference Publications (Full Written Paper - Refereed)
Publication Type Code e1

Show simple item record

Griffith University copyright notice