Voice Activity Detection Based on Short-Time Energy and Noise Spectrum Adaptation
. On the basis of the short-time energy of speech signal and the efficient method of noise statistics adaptation estimation proposed by Sohn et al., a new high robust voice activity detection (VAD) rule for any kinds of environmental noise is proposed in this paper. The accurate recognition rate of the new method is about five percent higher than that of Sohn's method on average, and also has the same merit of tracking the noise spectrum properly as Sohn's method. A great deal of simulation experiments shows that the new method is an efficient and robust voice activity detector.