Real Time Emulation of Parametric Guitar Tube Amplifier with Long Short Term Memory Neural Network

Schmitz, Thomas; Embrechts, Jean-Jacques

doi:10.5121/csit.2018.80511

Cited by 14 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [18] proposed a long short-term memory (LSTM) model, with many layers but a small hidden size in each layer, although the authors reported clearly audible differences between the resulting model and the target device. Schmitz and Embrechts have proposed a hybrid convolutional and recurrent model [19], as well as number of other recurrent, dense and convolutional networks [20]. In [21] we presented a single layer recurrent model along with a real-time C++ implementation.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Guitar Amplifier Emulation with Deep Learning

Wright

Damskägg²,

Juvela³

et al. 2020

Applied Sciences

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: Introductionmentioning

confidence: 99%

Real-Time Guitar Amplifier Emulation with Deep Learning

Wright

Damskägg²,

Juvela³

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…tube amplifier static waveshaping [11] tube amplifier dynamic nonlinear filters [12] distortion static waveshaping & numerical methods [13] distortion circuit simulation K-method & WDF [14] distortion circuit simulation Nodal DK [15] speaker, amplifier analytical method Volterra series [16] Moog ladder filter analytical method Volterra series [17] nonlinear power amplifier black-box Wiener & Hammerstein [18] with short-term memory distortion black-box Wiener [19] tube amplifer black-box Wiener-Hammerstein [20] equalization black-box end-to-end DNN [6] tube amplifier black-box end-to-end DNN [21] tube amplifier black-box end-to-end DNN [22] equalization & distortion black-box end-to-end DNN [7] tube amplifier black-box end-to-end DNN [9] tube amplifier, distortion black-box end-to-end DNN [23] distortion circuit simulation & DNN [24] compressor circuit simulation state-space [25] time-dependent nonlinear compressor black-box system-identification [26] compressor gray-box system-identification [27] compressor gray-box end-to-end DNN [28] ring modulator static waveshaping [29] phaser circuit simulation numerical methods [30] phaser circuit simulation Nodal DK [31] modulation based with OTAs circuit simulation WDF [32] flanger with BBDs circuit simulation Nodal DK [33] modulation based with BBDs circuit simulation & system-identification [32] time-varying Leslie speaker horn digital filter-based & system identification [34] Leslie speaker horn & woofer digital filter-based [35] Leslie speaker horn & woofer digital filter-based [36] flanger, chorus digital filter-based [30] modulation based with BBDs digital filter-based [37] modulation based gray-box system-identification…”

Section: Type Audio Effect Approach Referencementioning

confidence: 99%

“…The architecture is based on U-Net [47] and Time-Frequency [48] networks, where using input-output measurements and knowledge of the attack and release gate times are used to emulate different compressors and their respective controls. Similarly, RNNs for real-time black-box modeling of tube amplifiers and distortion pedals were explored in [23] and static configurations of tube amplifiers in [21,22]. A gray-box method is explored in [24], where a DNN is used to model the state-space system of nonlinear distortion circuits.…”

Section: Deep Learning For Audio Effects Modelingmentioning

confidence: 99%

Deep Learning for Black-Box Modeling of Audio Effects

2020

View full text Add to dashboard Cite

Virtual analog modeling of audio effects consists of emulating the sound of an audio processor reference device. This digital simulation is normally done by designing mathematical models of these systems. It is often difficult because it seeks to accurately model all components within the effect unit, which usually contains various nonlinearities and time-varying components. Most existing methods for audio effects modeling are either simplified or optimized to a very specific circuit or type of audio effect and cannot be efficiently translated to other types of audio effects. Recently, deep neural networks have been explored as black-box modeling strategies to solve this task, i.e., by using only input–output measurements. We analyse different state-of-the-art deep learning models based on convolutional and recurrent neural networks, feedforward WaveNet architectures and we also introduce a new model based on the combination of the aforementioned models. Through objective perceptual-based metrics and subjective listening tests we explore the performance of these models when modeling various analog audio effects. Thus, we show virtual analog models of nonlinear effects, such as a tube preamplifier; nonlinear effects with memory, such as a transistor-based limiter and nonlinear time-varying effects, such as the rotating horn and rotating woofer of a Leslie speaker cabinet.

show abstract

“…A feedforward variant of the WaveNet architecture [12] is trained for modeling of the vacuum-tube guitar preamplifier. Neural networks have been applied recently for tube amplifier modeling by several authors [13,14,15]. However, the previous models have not incorporated user controls, and are limited to a single setting of the amplifier.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Tube Amplifier Emulation

Damskägg

Juvela

Thuillier

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Analog audio effects and synthesizers often owe their distinct sound to circuit nonlinearities. Faithfully modeling such significant aspect of the original sound in virtual analog software can prove challenging. The current work proposes a generic data-driven approach to virtual analog modeling and applies it to the Fender Bassman 56F-A vacuum-tube amplifier. Specifically, a feedforward variant of the WaveNet deep neural network is trained to carry out a regression on audio waveform samples from input to output of a SPICE model of the tube amplifier. The output signals are pre-emphasized to assist the model at learning the high-frequency content. The results of a listening test suggest that the proposed model accurately emulates the reference device. In particular, the model responds to user control changes, and faithfully restitutes the range of sonic characteristics found across the configurations of the original device.

show abstract

Real Time Emulation of Parametric Guitar Tube Amplifier with Long Short Term Memory Neural Network

Cited by 14 publications

References 8 publications

Real-Time Guitar Amplifier Emulation with Deep Learning

Real-Time Guitar Amplifier Emulation with Deep Learning

Deep Learning for Black-Box Modeling of Audio Effects

Deep Learning for Tube Amplifier Emulation

Contact Info

Product

Resources

About