Audio Inpainting via $\ell_1$-Minimization and Dictionary Learning

TL;DR

This paper introduces an audio inpainting method combining dictionary learning with weighted $ ext{l}_1$-minimization, improving restoration quality by exploiting signal sparsity and adapting to energy loss in missing segments.

Contribution

It proposes a novel approach that integrates dictionary learning with weighted $ ext{l}_1$-minimization for enhanced audio inpainting within the sparsity framework.

Findings

Outperforms previous methods in SDR and ODG metrics.

Effectively restores missing audio segments with higher fidelity.

Demonstrates the benefit of combining dictionary learning with $ ext{l}_1$-minimization.

Abstract

Audio inpainting refers to signal processing techniques that aim at restoring missing or corrupted consecutive samples in audio signals. Prior works have shown that $\ell_1$- minimization with appropriate weighting is capable of solving audio inpainting problems, both for the analysis and the synthesis models. These models assume that audio signals are sparse with respect to some redundant dictionary and exploit that sparsity for inpainting purposes. Remaining within the sparsity framework, we utilize dictionary learning to further increase the sparsity and combine it with weighted $\ell_1$-minimization adapted for audio inpainting to compensate for the loss of energy within the gap after restoration. Our experiments demonstrate that our approach is superior in terms of signal-to-distortion ratio (SDR) and objective difference grade (ODG) compared with its original counterpart.