Inpainting of long audio segments with similarity graphs

TL;DR

This paper introduces a new audio inpainting method for long segments using similarity graphs that encode spectral features, enabling effective substitution of lost music data with smooth integration.

Contribution

It presents a novel graph-based approach for long audio segment inpainting that improves upon existing methods by leveraging spectral similarity and an optimization scheme.

Findings

High-quality inpainting results demonstrated on real-world music signals

Listening tests confirm the effectiveness of the proposed method

The approach outperforms traditional techniques in long audio gap filling

Abstract

We present a novel method for the compensation of long duration data loss in audio signals, in particular music. The concealment of such signal defects is based on a graph that encodes signal structure in terms of time-persistent spectral similarity. A suitable candidate segment for the substitution of the lost content is proposed by an intuitive optimization scheme and smoothly inserted into the gap, i.e. the lost or distorted signal region. Extensive listening tests show that the proposed algorithm provides highly promising results when applied to a variety of real-world music signals.