Spectral Entropy Based VAD Using Teager Energy Operator and HOS
In this paper, the authors presents Voice Activity Detection (VAD) algorithm for detecting voice in noisy environments. The presented robust VAD utilizes the Spectral Entropy (SE) with Teager Energy Operator (TEO) to provide a better representation of formant information resulting in high performance of classification of speech/non-speech priori to entropy based measurement. The spectral and TEO output with Higher order Statistics to detect voiced and unvoiced speech signal for noise like, white noise, pink noise and babble noise. The results show that the proposed algorithm has an overall better performance than the standard ITU-T G.729B VAD and Shen's entropy-based VAD.