Title :
Robust speech pulse detection using adaptive noise modelling and non-stationarity measure
Author :
Yoma, Nestor Becerra ; McInnes, Fergus ; Jack, Mervyn
Author_Institution :
Centre for Commun. Interface Res., Edinburgh Univ., UK
fDate :
30 Sep-1 Oct 1996
Abstract :
The problem of speech pulse detection with additive noise at 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: firstly, the autoregressive analysis of noise; secondly, spectral density comparison; and finally nonstationarity measure
Keywords :
FIR filters; autoregressive processes; spectral analysis; speech recognition; white noise; SNR; adaptive noise modelling; autoregressive analysis; nonstationarity measure; robust speech pulse detection; spectral density comparison; Finite impulse response filter; Least squares approximation; Noise generators; Noise measurement; Noise reduction; Noise robustness; Pulse measurements; Signal to noise ratio; Speech analysis; Speech enhancement;
Conference_Titel :
Interactive Voice Technology for Telecommunications Applications, 1996. Proceedings., Third IEEE Workshop on
Conference_Location :
Basking Ridge, NJ
Print_ISBN :
0-7803-3238-5
DOI :
10.1109/IVTTA.1996.552761
