duction techniques proposed in the art are expressed as a spectral

gain depending on the a priori SNR. In the well-known decision-

directed approach, the a priori SNR depends on the speech spec-

trum estimation in the previous frame. As a consequence the gain

function matches the previous frame rather than the current one

which degrades the noise reduction performance. We propose a

new method called Two-Step Noise Reduction (TSNR) technique

which solves this problem while maintaining the benefi ts of the

decision-directed approach. This method is analyzed and results

in voice communication and speech recognition context are given.-noise estimate