Janssen 2.0: Audio Inpainting in the Time-frequency Domain
arXiv:2409.06392 · doi:10.23919/EUSIPCO63237.2025.11226501
Abstract
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.
arXiv commentAccepted to EUSIPCO 2025
References in corpus (7)
- MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
- Deep Image Prior
- GACELA -- A generative adversarial context encoder for long audio inpainting
- Introducing SPAIN (SParse Audio INpainter)
- Audio Inpainting: Revisited and Reweighted
- Approximal operator with application to audio inpainting
- Tweaking autoregressive methods for inpainting of gaps in audio signals