Title :
Robust speech pulse detection using adaptive noise modelling
Author :
Yoma, N.B. ; McInnes, F. ; Jack, M.
Author_Institution :
Centre for Commun. Interface Res., Edinburgh Univ.
fDate :
7/18/1996 12:00:00 AM
Abstract :
The problem of speech pulse detection with additive noise at a signal-to-noise ratio (SNR) as low as 0 and -6 dB is addressed. The noise is assumed to be reasonably stationary and correlated. Three techniques have been examined: the autoregressive analysis of noise; spectral density comparison; and the non-stationarity measure
Keywords :
adaptive signal detection; autoregressive processes; correlation theory; speech recognition; adaptive noise modelling; additive noise; autoregressive analysis; correlated noise; nonstationarity measure; robust speech pulse detection; signal-to-noise ratio; spectral density; stationary noise;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19960892
