An improved voice activity detection algorithm employing speech enhancement preprocessing

In this paper, we first propose a new speech enhancement preprocessing algo rithm by combining power subtraction method and maximal ratio combining tec hnique, then apply it to both energy-based and statistical model-based VAD algorithm to improve the performance even in low SNR conditions. We also pe rform extensive computer simulations to demonstrate the performance improve ment of the proposed VAD algorithm employing the proposed speech enhancemen t preprocessing algorithm under various background noise environments.