SPEECH SIGNAL DETECTION IN A NOISY ENVIRONMENT USING NEURAL NETWORKS AND CEPSTRAL MATRICES
Juraj Ka, Gregor Rozinaj, Sergio Herrera-Garcia · 2004
In this article a new exible speech detection method comprising two relatively modern approaches like articial neural networks (ANN) and cepstral matrices is presented. Cepstral matrices obtained via linear prediction coecien ts were chosen as the eligible speech features. This technique is known to provide reliable log spectrum estimation at a low cost. Furthermore, both spectral and time characteristics can be ecien tly, which is an essential aim here. Several WSS noises and dieren t SNR settings were tested. In the range of 3 to 13 dB the ANN approach remarkably outperformed the energy and zero crossing method and improved the accuracy of the other algorithm based on cepstral matrices as well. K e y w o r d s: cepstral matrices, neural networks, MLP, speech detection, CLPC vectors, WSS noises