Application of GM(1,1) Model to Voice Activity Detection

In this paper, a novel approach to apply GM(1,1) model in voice activity detection (VAD) is presented. The approach is termed as grey VAD (GVAD). In GVAD, the GM(1,1) model is used to estimate non-stationary noise in noisy speech and therefore signal component where an additive signal model is assumed. By estimated noise and signal, the signal-to-noise ratio (SNR) is calculated. Based on an adaptive threshold, the speech and non-speech segments are determined. The proposed GVAD is performed in the time domain and thus has less computational complexity than those frequency domain approaches. Through simulation, the GVAD is verified by cases with non-stationary noise. The result indicates that the proposed GVAD is able to detect voice activity appropriately.