A unified approach to speech enhancement and voice activity detection

Abstract

In this paper, a unified 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 and robust VAD algorithm is implemented for the VAD block of the unified system. The newly proposed VAD algorithm uses a periodicity measure and an energy measure obtained from spectral energy distribution and spectral energy difference of the input speech data. For the speech enhancement block, the modified Wiener filtering (MWF) approach is utilized. It has been shown that the utilization of information exchange between the VAD and MWF algorithms in the unified system increases the performance of both algorithms and the proposed unified system improves the robustness of a speech recognition system significantly. Both of the enhanced algorithms are noniterative. Therefore, the proposed unified system is computationally attractive for real-time applications.