paper-with-me

홈 › Papers

Janssen 2.0: Audio Inpainting in the Time-frequency Domain

2024-09-10 · Ondřej Mokrý, Peter Balušík, Pavel Rajmic

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.

📄 PDF Abstract BibTeX arXiv:2409.06392

Code (1)

rajmic/spectrogram-inpainting 공식 구현 tf

Tasks

Audio inpainting

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

Tweaking autoregressive methods for inpainting of gaps in audio signals

2024-03-07 · Ondřej Mokrý, Pavel Rajmic

A novel variant of the Janssen method for audio inpainting is presented and compared to other popular audio inpainting methods based on autoregressive (AR) modeling. Both conceptual differences and practical implications…

Audio inpainting

Flexible framework for audio reconstruction

2020-07-29

The paper presents a unified, flexible framework for the tasks of audio inpainting, declipping, and dequantization. The concept is further extended to cover analogous degradation models in a transformed domain, e.g. quan…

Audio inpaintingQuantization

Algorithms for audio inpainting based on probabilistic nonnegative matrix factorization

2022-06-28 · Ondřej Mokrý, Paul Magron, Thomas Oberlin, Cédric Févotte

Audio inpainting, i.e., the task of restoring missing or occluded audio signal samples, usually relies on sparse representations or autoregressive modeling. In this paper, we propose to structure the spectrogram with non…

Audio inpainting

Audio inpainting of music by means of neural networks

2018-10-29 · Andrés Marafioti, Nicki Holighaus, Piotr Majdak, Nathanaël Perraudin

We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The…

Audio GenerationAudio inpainting

Approximal operator with application to audio inpainting

2020-05-04 · Ondřej Mokrý, Pavel Rajmic

In their recent evaluation of time-frequency representations and structured sparsity approaches to audio inpainting, Lieb and Stark (2018) have used a particular mapping as a proximal operator. This operator serves as th…

Audio inpainting