A new algorithm for voice activity detection based on wavelet packets

Speech constitutes much of the communicated information; most other perceived audio signals do not carry nearly as much information. Indeed, much of the non-speech signals maybe classified as dasianoisepsila in human communication. The process of separating conversational speech and noise is termed voice activity detection (VAD). This paper describes a new approach to VAD which is based on the wavelet packet transform (WPT). Our algorithm utilizes the differences between spectral distribution of human speech (voice) and general noise. First, the algorithm performs wavelet transform on the signal resulting in its decomposition into subbands using coefficients of WPT, then it detects the voice within the signal by comparing the subband energy of components between detail and approximation coefficients. Computer simulation results are given to illustrate the effectiveness of our new VAD algorithms.