Power Level In Dual − Microphone System

Abstract

This paper deals with speech enhancement in dual-microphone system using cross power spectral densities. The performance of the proposed algorithm relies on a good estimation of the acoustic channel and speech and noise statistics. In this work we present a speech enhancement system that uses the differences of power spectral densities level as the condition distinguishes whether noise, whether speech signal. The available dual-channel information is exploited to obtain more reliable estimates of clean speech statistics. Our proposal is evaluated in a reverberant room and mixtures of various diffuse noise. The experimental results show that our system achieves improvements in terms of noise reduction, low speech distortion and remain the desired signal.