Research Article
Variable Step Size NLMS Algorithm for Speech Dereverberation
|
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
| Volume 179 - Issue 39 |
| Published: May 2018 |
| Authors: P. Sony, K. Kiran, Ch. Divya Susmitha |
10.5120/ijca2018916816
|
P. Sony, K. Kiran, Ch. Divya Susmitha . Variable Step Size NLMS Algorithm for Speech Dereverberation. International Journal of Computer Applications. 179, 39 (May 2018), 44-47. DOI=10.5120/ijca2018916816
@article{ 10.5120/ijca2018916816,
author = { P. Sony,K. Kiran,Ch. Divya Susmitha },
title = { Variable Step Size NLMS Algorithm for Speech Dereverberation },
journal = { International Journal of Computer Applications },
year = { 2018 },
volume = { 179 },
number = { 39 },
pages = { 44-47 },
doi = { 10.5120/ijca2018916816 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2018
%A P. Sony
%A K. Kiran
%A Ch. Divya Susmitha
%T Variable Step Size NLMS Algorithm for Speech Dereverberation%T
%J International Journal of Computer Applications
%V 179
%N 39
%P 44-47
%R 10.5120/ijca2018916816
%I Foundation of Computer Science (FCS), NY, USA
Abstract
In many speech communication applications, the recorded speech signal is subject to reflections on the room walls and other objects on its way from the source to the microphone. Then resulting signal is called reverberated, which decrease Automatic Speech Recognition (ASR) performance and loss of intelligibility to listeners. However, it is still a challenging problem because of the nature of common room impulse response (RIR). RIR is generated artificially based on parameters of the room and its intensity depends on the size, shape, dimensions and materials used in the construction of the room. Here proposed an LMS-like gradient adaptive maximizing algorithm that maximizes the kurtosis of the LP residuals of the speech signal to the clean speech. The method used in this is maximizes kurtosis of LP residual of speech to removing reverberation from degraded speech. The performances of these methods are analysed using Reverberation Index (RR) and Speech Distortion (SD) parameters.
References
- P. A. Naylor and N. D. Gaubitch, Eds., Speech Dereverberation. Springer 2012- 05-09.
- B.Yegnanarayana and P. S. Murthy, Enhancement of reverberant speech using LPResidual Signal," IEEE Transactions on Speech and Audio Processing, vol. 8, no. 3,pp 267{281}, May 2000.
- B. W. Gillespie, D. A. F. Florencio, and H. S. Malvar, Speech dereverberation via Maximum-kurtosis subband adaptive filtering," in ICASSP '01: IEEE International Conference on Acoustics, Speech, and Signal Processing 2001, vol. 6, pp. 3701{3704}, IEEE.
- J. Benesty,T. Gaensler, D. R. Morgan, M. M. Sondhi, and S. L. Gay,Advances in Network and Acoustic Echo Cancellation. Berlin, Germany:Springer-Verlag, 2001.
- H.-C. Shin,A.H. Sayed, and W.-J. Song,“Variable step-size NLMS and affine projection algorithms,” IEEE Signal Process. Lett.vol. 11, no. 2, pp. 132–135, Feb. 2004.
- J. Benesty, H. Rey, L. Rey Vega, and S.Tressens.“A nonparametricVSSNLMS algorithm,” IEEE Signal Process. Lett, vol. 13, no. 10, pp. 581–584, Oct. 2006.
Index Terms
Keywords