Deep Learning for Tube Amplifier Emulation

Damskägg, Eero-Pekka; Juvela, Lauri; Thuillier, Etienne; Välimäki, Vesa

doi:10.1109/icassp.2019.8682805

Cited by 31 publications

(47 citation statements)

References 15 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Output signal In previous work [23], the outputs of the convolutional layers were fed to a three layer post-processing module with 1 × 1 convolutions and nonlinear activation functions. In convolutional neural network terminology, a 1 × 1 convolution refers to a matrix multiplication applied at each time step in the signal.…”

Section: Conditioning (User Controls)mentioning

confidence: 99%

“…This paper focuses on a model we proposed [23] for nonlinear cicuit black-box modelling, that was based on the WaveNet convolutional neural network [24]. The neural network model is made up of a series of convolutional layers, with each layer consisting of a dilated filter followed by a dynamically gated nonlinear activation function.…”

Section: Introductionmentioning

confidence: 99%

“…The neural network model is made up of a series of convolutional layers, with each layer consisting of a dilated filter followed by a dynamically gated nonlinear activation function. In [23] listening tests were conducted to validate the performance of the model when emulating the Fender Bassman tube amplifier. Following from this, we presented models, with a focus on real-time performance, of three guitar distortion effects: the Ibanez Tube Screamer, the Boss DS-1, and the Electro-Harmonix Big Muff Pi [25].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Guitar Amplifier Emulation with Deep Learning

Wright

Damskägg²,

Juvela³

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

This article investigates the use of deep neural networks for black-box modelling of audio distortion circuits, such as guitar amplifiers and distortion pedals. Both a feedforward network, based on the WaveNet model, and a recurrent neural network model are compared. To determine a suitable hyperparameter configuration for the WaveNet, models of three popular audio distortion pedals were created: the Ibanez Tube Screamer, the Boss DS-1, and the Electro-Harmonix Big Muff Pi. It is also shown that three minutes of audio data is sufficient for training the neural network models. Real-time implementations of the neural networks were used to measure their computational load. To further validate the results, models of two valve amplifiers, the Blackstar HT-5 Metal and the Mesa Boogie 5:50 Plus, were created, and subjective tests were conducted. The listening test results show that the models of the first amplifier could be identified as different from the reference, but the sound quality of the best models was judged to be excellent. In the case of the second guitar amplifier, many listeners were unable to hear the difference between the reference signal and the signals produced with the two largest neural network models. This study demonstrates that the neural network models can convincingly emulate highly nonlinear audio distortion circuits, whilst running in real-time, with some models requiring only a relatively small amount of processing power to run on a modern desktop computer.

show abstract

Section: Conditioning (User Controls)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Guitar Amplifier Emulation with Deep Learning

Wright

Damskägg²,

Juvela³

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning architectures for black-box modeling of audio effects have been researched lately for linear effects such as equalization [18]; nonlinear memoryless effects such as tube amplifiers [19,20,21]; nonlinear effects with temporal dependencies such as compressors [22]; and linear and nonlinear time-varying effects such as flanging or ring modulation [23]. Deep learning for dereverberation has become a heavily researched field [24,25], although applying artificial reverberation or modeling plate and spring reverb with deep neural networks (DNN) has not been explored yet.…”

Section: Introductionmentioning

confidence: 99%

Modeling Plate and Spring Reverberation Using A DSP-Informed Deep Neural Network

Ramírez

Benetos

Reiss

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Plate and spring reverberators are electromechanical systems first used and researched as means to substitute real room reverberation. Nowadays they are often used in music production for aesthetic reasons due to their particular sonic characteristics. The modeling of these audio processors and their perceptual qualities is difficult since they use mechanical elements together with analog electronics resulting in an extremely complex response. Based on digital reverberators that use sparse FIR filters, we propose a signal processinginformed deep learning architecture for the modeling of artificial reverberators. We explore the capabilities of deep neural networks to learn such highly nonlinear electromechanical responses and we perform modeling of plate and spring reverberators. In order to measure the performance of the model, we conduct a perceptual evaluation experiment and we also analyze how the given task is accomplished and what the model is actually learning.

show abstract

“…Deep learning has demonstrated great utility at such diverse audio signal processing tasks as classification, 13,14 onset detection, 15 source separation, 16 event detection, 17 dereverberation, 18,19 denoising, 20 formant estimation, 21 remixing, 22 and synthesis, [23][24][25][26] as well as dynamic range compression to automate the mastering process. 27 In the area of audio component modeling, deep learning has been used to model tube amplifiers 28 and most recently guitar distortion pedals. 29 Besides creating specific effects, efforts have been underway to explore how varied are the types of effects which can be learned from a single model, 30 to which this paper comprises a contribution.…”

Section: Introductionmentioning

confidence: 99%

Profiling musical audio processing effects with deep neural networks

Hawley

Colburn

Mimilakis

2018

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

In this work we present a data-driven approach for predicting the behavior of (i.e., profiling) a given non-linear audio signal processing effect (henceforth "audio effect"). Our objective is to learn a mapping function that maps the unprocessed audio to the processed by the audio effect to be profiled, using time-domain samples.To that aim, we employ a deep auto-encoder model that is conditioned on both time-domain samples and the control parameters of the target audio effect. As a test-case study, we focus on the offline profiling of two dynamic range compression audio effects, one software-based and the other analog. Compressors were chosen because they are a widely used and important set of effects and because their parameterized nonlinear timedependent nature makes them a challenging problem for a system aiming to profile "general" audio effects. Results from our experimental procedure show that the primary functional and auditory characteristics of the compressors can be captured, however there is still sufficient audible noise to merit further investigation before such methods are applied to real-world audio processing workflows.

show abstract

Deep Learning for Tube Amplifier Emulation

Cited by 31 publications

References 15 publications

Real-Time Guitar Amplifier Emulation with Deep Learning

Real-Time Guitar Amplifier Emulation with Deep Learning

Modeling Plate and Spring Reverberation Using A DSP-Informed Deep Neural Network

Profiling musical audio processing effects with deep neural networks

Contact Info

Product

Resources

About