In this work, we present an algorithm that switches between theenergy and the entropy based voice activity detectors (VADs)to provide an improved performance under varying signal tonoise ratio (SNR) conditions. The motivation for switch-ing has come from the observed complementary behaviorin the noise estimation performances of energy and entropybased voice activity detectors when evaluated over a range of—5 dB < SNR < 30 dB. At lower SNRs the entropy basedvoice activity detector outperformed the energy based one,whereas at higher SNRs interestingly the opposite trend wasnoted. The proposed online switching algorithm has a responsetime of 0.5 second and it achieves the optimal performance ofeither of the off-line VADs under fixed SNR conditions.
展开▼