A bioinspired spectro-temporal domain for sound denoising

Abstract

The representation of sound signals at the cochlea and au- ditory cortical level has been studied as an alternative to classical anal- ysis methods. In this work, we put forward a recently proposed feature extraction method called approximate auditory cortical representation, based on an approximation to the statistics of discharge patterns at the primary auditory cortex. The approach here proposed estimates a non- negative sparse coding with a combined dictionary of atoms calculated from clean signal and noise. The denoising is carried out on noisy signals by the reconstruction of the signal discarding the atoms corresponding to the noise. Results on synthetic and real data show that the proposed method improves the quality of the signals, mainly under severe degra- dation. This communication corresponds to a journal paper published in 2015 in DSP (Elsevier).