Saved in:
Bibliographic Details
Main Authors: Balušík, Peter, Rajmic, Pavel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.18535
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911423737626624
author Balušík, Peter
Rajmic, Pavel
author_facet Balušík, Peter
Rajmic, Pavel
contents We address the problem of time-frequency audio inpainting, where the goal is to fill missing spectrogram portions with reliable 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 and the autoregression-based approach known as Janssen-TF. Our proposed approach surpassed these methods by a large margin in the objective evaluation as well as in the conducted subjective listening test, improving the state of the art. In addition, the reconstructions are obtained with a substantially reduced computational cost compared to alternative methods.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18535
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Audio Inpainting in Time-Frequency Domain with Phase-Aware Prior
Balušík, Peter
Rajmic, Pavel
Audio and Speech Processing
Sound
We address the problem of time-frequency audio inpainting, where the goal is to fill missing spectrogram portions with reliable 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 and the autoregression-based approach known as Janssen-TF. Our proposed approach surpassed these methods by a large margin in the objective evaluation as well as in the conducted subjective listening test, improving the state of the art. In addition, the reconstructions are obtained with a substantially reduced computational cost compared to alternative methods.
title Audio Inpainting in Time-Frequency Domain with Phase-Aware Prior
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2601.18535