The objective of audio inpainting is to fill a gap in a signal, either to be meaningful or even to reconstruct the original signal. We propose a novel approach applying sparse modeling in the time-frequency (TF) domain. In particular, we develop a dictionary learning technique which deforms a given Gabor frame such that the sparsity of the analysis coefficients of the resulting frame is maximized. A suitable modification of the SParse Audio Inpainter (SPAIN) allows to exploit the obtained sparsity gain and, hence, to benefit from the learned dictionary. Our experiments demonstrate that our methods outperforms several state-of-the-art audio inpainting techniques in terms of signal-to-noise ratio (SNR) and objective difference grade (ODG).

Authors: Tauboeck, Georg; Rajbamshi, Shristi; Balazs, Peter
Affiliation: Acoustics Research Institute, Austrian Academy of Sciences, Vienna, Austria
AES Convention: 149 (October 2020) Paper Number: 10402
Publication Date: October 22, 2020 Import into BibTeX
Subject: Audio Processing
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=20939

Download Now (1.2 MB)

This paper is Open Access which means you can download it for free.

Learn more about the AES E-Library

E-Library Location:   /conv/149/10402.pdf

Start a discussion about this paper!