Voice activity detection based on adjustable linear prediction and GARCH models

We propose a method for voice activity detection (VAD) that employs a class of the Autoregressive–Generalized Autoregressive Conditional Heteroskedasticity (AR-GARCH) model. As regards correlated speech signals, we represent the AR part of the AR-GARCH model with a state-space to obtain the appropriate linear prediction error series. By applying the GARCH model to the residual, we estimate the conditional variance sequences corresponding to the voice activity parts. To detect voice activity, we establish an appropriate threshold for the conditional variance sequences. To confirm the performance of our proposed VAD method, we conduct experiments using speech signals with real background noise (signal-to-noise ratios (SNRs) of 10, 5 and 0 dB) of an airport and a street. Furthermore, using receiver operating characteristics curves and equal error rates, we compare our results with those of previous standardized VAD algorithms (ITU-T G.729B, ETSI ES 202 050, and ETSI EN 301 708) as well as recently developed methods (VAD with long-term spectral divergence, likelihood ratio tests, and higher-order statistics for VAD). In terms of the signals with background noise at an SNR of 0 dB, the experimental results show a significant performance improvement compared with standardized VAD algorithms and more than 10% improvement compared with recently developed VAD methods.