Algorithms for audio inpainting based on probabilistic nonnegative matrix factorization

TL;DR

This paper introduces probabilistic nonnegative matrix factorization algorithms for audio inpainting, effectively restoring missing audio segments with competitive results compared to existing methods.

Contribution

It develops novel EM and alternating minimization algorithms for audio inpainting using probabilistic NMF, addressing both parameter estimation and missing sample reconstruction.

Findings

Algorithms show fast convergence.

Achieve competitive inpainting performance.

Effective for restoring short to middle gaps in music.

Abstract

Audio inpainting, i.e., the task of restoring missing or occluded audio signal samples, usually relies on sparse representations or autoregressive modeling. In this paper, we propose to structure the spectrogram with nonnegative matrix factorization (NMF) in a probabilistic framework. First, we treat the missing samples as latent variables, and derive two expectation-maximization algorithms for estimating the parameters of the model, depending on whether we formulate the problem in the time- or time-frequency domain. Then, we treat the missing samples as parameters, and we address this novel problem by deriving an alternating minimization scheme. We assess the potential of these algorithms for the task of restoring short- to middle-length gaps in music signals. Experiments reveal great convergence properties of the proposed methods, as well as competitive performance when compared to state-of-the-art audio inpainting techniques.