Compensating for denoising artifacts

Noise degrades speech signals, affecting their perceptual quality, intelligibility, as well as their downstream processing, e.g. coding or recognition. One obvious solution to this is to denoise the signals, but denoising algorithms filter out an estimate of noise, which is often inexact. As a result, denoising can attenuate spectral components of speech, which may enhance perceptual quality but further reduce it´s intelligibility. We address the latter issue and propose a method to restore lost spectral components in denoised speech. Our algorithm modifies the standard NMF formulation to represent clean speech as a composition of bases, and denoised speech as a composition of distortions of these bases. By decomposing the denoised signal into a composition of the distorted bases, the corresponding clean signal can be estimated as an identical composition of the clean bases.