Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

audio-10

Audio inpainting

3260 papers • 126 benchmarks • 313 datasets

Filling in holes in audio data

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in audio-inpainting-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find audio-inpainting-10 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Flexible framework for audio reconstruction

Ondřej Mokrý, P. Rajmic, Pavel Záviška•Wed Apr 22 2020

The paper presents a unified, flexible framework for the tasks of audio inpainting, declipping, and dequantization that is extended to cover analogous degradation models in a transformed domain, e.g. quantization of the signal's time-frequency coefficients.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Algorithms for audio inpainting based on probabilistic nonnegative matrix factorization

Ondvrej Mokr'y, Paul Magron, T. Oberlin, C'edric F'evotte•Mon Jun 27 2022

This paper proposes to structure the spectrogram with nonnegative matrix factorization (NMF) in a probabilistic framework, and derives two expectation-maximization algorithms for estimating the parameters of the model, depending on whether the problem in the time- or time-frequency domain.

14 0

Paper Graph

Audio Inpainting of Music by Means of Neural Networks

Andrés Marafioti, P. Majdak, Nicki Holighaus, Nathanael Perraudin•Sun Oct 28 2018

For music, the DNN significantly outperformed the reference method, demonstrating a generally good usability of the proposed DNN structure for inpainting complex audio signals like music.

19 0

Paper Graph

Audio inpainting with generative adversarial network

P. Ebner, Amr Eltelt•Thu Mar 12 2020

The proposed model outperforms the classical WGAN model and improves the reconstruction of high-frequency content and better results for instruments where the frequency spectrum is mainly in the lower range where small noises are less annoying for human ear and the inpainting part is more perceptible.

28 0

Paper Graph

Approximal operator with application to audio inpainting

Ondřej Mokrý, P. Rajmic•Sun May 03 2020

Surprisingly, in most cases, such an approximation is shown to provide even better numerical results in audio inpainting compared to its proper counterpart, while being computationally much more effective.

7 0

Paper Graph

Solving Audio Inverse Problems with a Diffusion Model

J. Lehtinen, Eloi Moliner, V. Välimäki•Wed Oct 26 2022

The results show that CQT-Diff outperforms the compared baselines and ablations in audio bandwidth extension and, without retraining, delivers competitive performance against modern baselines in audio inpainting and declipping.

79 0

Paper Graph

Msanii: High Fidelity Music Synthesis on a Shoestring Budget

Kinyugo Maina•Sun Jan 15 2023

This work presents Msanii, a novel diffusion-based model for synthesizing long-context, high-fidelity music efficiently that combines the expressiveness of mel spectrograms, the generative capabilities of diffusion models, and the vocoding capabilities of neural vocoders.

9 0

Paper Graph

Diffusion-Based Audio Inpainting

Eloi Moliner, V. Välimäki•Tue May 23 2023

The proposed method using an unconditionally trained generative model, which can be conditioned in a zero-shot fashion for audio inpainting, and is able to regenerate gaps of any size, can be applied to restoring sound recordings that suffer from severe local disturbances or dropouts, which must be reconstructed.

22 0

Paper Graph

Adding a benchmark result helps the community track progress.

Audio inpainting | State-of-the-Art