A uni¿ed approach to speech enhancement and voice activity detection

In this work, a uni¿ed system for voice activity detection (VAD) and speech enhancement is proposed. In the proposed system, there is mutual exchange of information between VAD and speech enhancement blocks. A new, robust and low complexity VAD algorithm is implemented for the VAD block of the uni¿ed system. The newly proposed VAD algorithm uses a periodicity measure and an energy measure obtained from spectral energy distribution and spectral energy di¿erence of the input speech data. For the speech enhancement block, the Modi¿ed Wiener Filtering (MWF) algorithm is utilized. It has been shown that the utilization of information exchange between the VAD and MWF algorithms in the uni¿ed system increases the performance of both algorithms and the proposed uni¿ed system improves the robustness of a speech recognition system signi¿cantly. Both of the enhanced algorithms are non-iterative. Therefore, the proposed uni¿ed system is computationally attractive for real-time applications.