Show & Tell: Phase-Aware Single-channel Speech Enhancement
Pejman Mowlaee, Mario Kaoru Watanabe, Rahim Saeidi · 2013
Many short-time Fourier transform (STFT) based singlechannel speech enhancement algorithms are focused on estimating clean speech spectral amplitude from the noisy observed signal in order to suppress the additive noise. To this end, the state-of-the-art speech enhancement algorithms, employ noisy amplitude information and correspondingly a priori and a posteriori SNRs while they use no information about the speech phase spectrum. In this show and tell we demonstrate our recent progress on developing novel ideas towards incorporating phase information in solving single-channel speech enhancement problem.