audio-7

Audio Effects Modeling

3260 papers • 126 benchmarks • 313 datasets

Modeling of audio effects such as reverberation, compression, distortion, etc.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in audio-effects-modeling-7

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find audio-effects-modeling-7 models and implementations

Datasets

SignalTrain LA2A Dataset

DiffVox

Subtasks

Pitch control Timbre Interpolation

Most implemented papers

SignalTrain: Profiling Audio Compressors with Deep Neural Networks

Scott H. Hawley, Benjamin Colburn, S. I. Mimilakis•Mon May 27 2019

A data-driven approach for predicting the behavior of a given non-linear audio signal processing effect (henceforth "audio effect") using a deep auto-encoder model that is conditioned on both time-domain samples and the control parameters of the target audio effect.

13

Content

0

Paper Graph

Differentiable All-pole Filters for Time-varying Audio Systems

Chin-Yun Yu, Gyorgy Fazekas, Christopher Mitcheltree, Alistair Carson, Stefan Bilbao, Joshua D. Reiss•Wed Apr 10 2024

This work re-expresses a time-varying all-pole filter to backpropagate the gradients through itself, so the filter implementation is not bound to the technical limitations of automatic differentiation frameworks and can be employed within audio systems containing filters with poles for efficient gradient evaluation.

14 0

Paper Graph

Estimation and Restoration of Unknown Nonlinear Distortion Using Diffusion

Eloi Moliner, Michal vSvento, Lauri Juvela, Alec Wright, Vesa Valimaki•Thu Jan 09 2025

Experiments on distorted speech show that the proposed blind method outperforms general-purpose speech enhancement techniques and restores the original voice quality, and comparisons with informed and supervised restoration methods show that the proposed blind method is at least as good as they are in terms of objective metrics.

2 0

Paper Graph

Adding a benchmark result helps the community track progress.