Abstract:We address the problem of time-frequency audio inpainting, where the goal is to fill missing spectrogram portions with consistent information. Despite recent advances, existing approaches still face limitations in both reconstruction quality and computational efficiency. To bridge this gap, we propose a method that utilizes a phase-aware signal prior which exploits estimates of the instantaneous frequency. An optimization problem is formulated and solved using the generalized Chambolle-Pock algorithm. The proposed method is evaluated against other time-frequency inpainting methods, specifically a deep-prior audio inpainting neural network, the autoregression-based approach known as Janssen-TF, and a sparsity-driven baseline. For short gap durations, the proposed approach achieves superior SNR, while performing comparably to Janssen-TF on larger gaps. In terms of perceptual quality (both objective and subjective), the proposed method consistently outperforms existing methods across all gap lengths. In addition, the reconstructions are obtained with a substantially reduced computational cost compared to alternative methods.
From: Peter Balušík [view email]
[v1]
Mon, 26 Jan 2026 14:40:41 UTC (754 KB)
[v2]
Thu, 5 Feb 2026 16:37:02 UTC (752 KB)
[v3]
Fri, 21 Aug 2026 07:42:09 UTC (720 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。