Differentiable Artificial Reverberation

Lee, Sungho; Choi, Hyeong-Seok; Lee, Kyogu

doi:10.1109/taslp.2022.3193298

Cited by 17 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…differentiable AFXs as specialized neural networks layers with interpretable parameters [4,5,6]. Because they are differentiable, they can be integrated transparently in a neural network.…”

Section: Related Workmentioning

confidence: 99%

Blind Estimation of Audio Effects Using an Auto-Encoder Approach and Differentiable Digital Signal Processing

Peladeau,

Peeters

2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Blind Estimation of Audio Effects (BE-AFX) aims at estimating the audio effects (AFXs) applied to an original, unprocessed audio sample solely based on the processed audio sample. To train such a system traditional approaches optimize a loss between ground truth and estimated AFX parameters. This involves knowing the exact implementation of the AFXs used for the process. In this work, we propose an alternative solution that eliminates the requirement for knowing this implementation. Instead, we introduce an auto-encoder approach, which optimizes an audio quality metric. We explore, suggest, and compare various implementations of commonly used mastering AFXs, using differential signal processing or neural approximations. Our findings demonstrate that our auto-encoder approach yields superior estimates of the audio quality produced by a chain of AFXs, compared to the traditional parameter-based approach, even if the latter provides a more accurate parameter estimation.

show abstract

“…differentiable AFXs as specialized neural networks layers with interpretable parameters [4,5,6]. Because they are differentiable, they can be integrated transparently in a neural network.…”

Section: Related Workmentioning

confidence: 99%

Blind Estimation of Audio Effects Using an Auto-Encoder Approach and Differentiable Digital Signal Processing

Peladeau,

Peeters

2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Differentiable signal processing has also been applied in tasks related to audio engineering, such as audio effect modelling (Kuznetsov et al, 2020;Lee et al, 2022;Carson et al, 2023), automatic mixing and intelligent music production (Martinez Ramirez et al, 2021;Steinmetz et al, 2022a), and filter design (Colonel et al, 2022). Whilst many innovations from this work have found use in synthesis, and vice versa, we do not set out to comprehensively review these tasks areas.…”

Section: Authors Year Contributionsmentioning

confidence: 99%

A review of differentiable digital signal processing for music and speech synthesis

Hayes,

Shier,

Fazekas

et al. 2024

Front. Signal Process.

View full text Add to dashboard Cite

The term “differentiable digital signal processing” describes a family of techniques in which loss function gradients are backpropagated through digital signal processors, facilitating their integration into neural networks. This article surveys the literature on differentiable audio signal processing, focusing on its use in music and speech synthesis. We catalogue applications to tasks including music performance rendering, sound matching, and voice transformation, discussing the motivations for and implications of the use of this methodology. This is accompanied by an overview of digital signal processing operations that have been implemented differentiably, which is further supported by a web book containing practical advice on differentiable synthesiser programming (https://intro2ddsp.github.io/). Finally, we highlight open challenges, including optimisation pathologies, robustness to real-world conditions, and design trade-offs, and discuss directions for future research.

show abstract

“…Computing ℓ on sweeps instead of impulses provides a better match of the LR gain. Loss functions used for similar tasks [22,43] inspired the definition of ℓ as the mean absolute difference between the multi-resolution mel-spectrograms of L b s and Ls . The mel-spectrogram in dB M f -Short-Time Fourier Transform, followed by the filter-bank mapping to the mel scale and dB conversion-aims at a perceptually motivated loss.…”

Section: Artificial Late Reverberation Matchingmentioning

confidence: 99%

Co-Immersion in Audio Augmented Virtuality: The Case Study of a Static and Approximated Late Reverberation Algorithm

Fantini,

Presti,

Geronazzo

et al. 2023

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Differentiable Artificial Reverberation

Cited by 17 publications

References 36 publications

Blind Estimation of Audio Effects Using an Auto-Encoder Approach and Differentiable Digital Signal Processing

Blind Estimation of Audio Effects Using an Auto-Encoder Approach and Differentiable Digital Signal Processing

A review of differentiable digital signal processing for music and speech synthesis

Co-Immersion in Audio Augmented Virtuality: The Case Study of a Static and Approximated Late Reverberation Algorithm

Contact Info

Product

Resources

About