Saved in:
Bibliographic Details
Main Authors: Mokrý, Ondřej, Balušík, Peter, Rajmic, Pavel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.06392
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918237040541696
author Mokrý, Ondřej
Balušík, Peter
Rajmic, Pavel
author_facet Mokrý, Ondřej
Balušík, Peter
Rajmic, Pavel
contents The paper focuses on inpainting missing parts of an audio signal spectrogram, i.e., estimating the lacking time-frequency coefficients. The autoregression-based Janssen algorithm, a state-of-the-art for the time-domain audio inpainting, is adapted for the time-frequency setting. This novel method, termed Janssen-TF, is compared with the deep-prior neural network approach using both objective metrics and a subjective listening test, proving Janssen-TF to be superior in all the considered measures.
format Preprint
id arxiv_https___arxiv_org_abs_2409_06392
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Janssen 2.0: Audio Inpainting in the Time-frequency Domain
Mokrý, Ondřej
Balušík, Peter
Rajmic, Pavel
Audio and Speech Processing
Sound
The paper focuses on inpainting missing parts of an audio signal spectrogram, i.e., estimating the lacking time-frequency coefficients. The autoregression-based Janssen algorithm, a state-of-the-art for the time-domain audio inpainting, is adapted for the time-frequency setting. This novel method, termed Janssen-TF, is compared with the deep-prior neural network approach using both objective metrics and a subjective listening test, proving Janssen-TF to be superior in all the considered measures.
title Janssen 2.0: Audio Inpainting in the Time-frequency Domain
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2409.06392