Detail publikačního výsledku

Janssen 2.0: Audio Inpainting in the Time-frequency Domain

MOKRÝ, Ondřej; BALUŠÍK, Peter; RAJMIC, Pavel

Originální název

Janssen 2.0: Audio Inpainting in the Time-frequency Domain

Anglický název

Janssen 2.0: Audio Inpainting in the Time-frequency Domain

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

audio inpainting; autoregression; deep prior; DPAI; time-frequency; spectrogram

Klíčová slova v angličtině

audio inpainting; autoregression; deep prior; DPAI; time-frequency; spectrogram

Autoři

MOKRÝ, Ondřej; BALUŠÍK, Peter; RAJMIC, Pavel

Rok RIV

2026

Vydáno

08.09.2025

ISBN

978-9-46-459362-4

Kniha

2025 33rd European Signal Processing Conference (EUSIPCO)

Strany od

301

Strany do

305

Strany počet

5

URL

https://ieeexplore.ieee.org/document/11226501

BibTex

@inproceedings{BUT198904,
  author="Ondřej {Mokrý} and Peter {Balušík} and Pavel {Rajmic}",
  title="Janssen 2.0: Audio Inpainting in the Time-frequency Domain",
  booktitle="2025 33rd European Signal Processing Conference (EUSIPCO)",
  year="2025",
  pages="301--305",
  doi="10.23919/EUSIPCO63237.2025.11226501",
  isbn="978-9-46-459362-4",
  url="https://ieeexplore.ieee.org/document/11226501"
}