Next Article in Journal
Photoacoustic Imaging for Management of Breast Cancer: A Literature Review and Future Perspectives
Next Article in Special Issue
A History of Audio Effects
Previous Article in Journal
Laser Metal Deposition of Ti6Al4V—A Brief Review
Previous Article in Special Issue
Deep Learning for Black-Box Modeling of Audio Effects

Real-Time Guitar Amplifier Emulation with Deep Learning †

Acoustics Laboratory, Department of Signal Processing and Acoustics, Aalto University, FI-02150 Espoo, Finland
Neural DSP Technologies, FI-00150 Helsinki, Finland
Author to whom correspondence should be addressed.
This paper is an extended version of our paper published in the Proceedings of the 16th International Sound and Music Computing Conference SMC-19 in Malaga, Spain, 28–31 May 2019.
Appl. Sci. 2020, 10(3), 766;
Received: 12 December 2019 / Revised: 14 January 2020 / Accepted: 15 January 2020 / Published: 21 January 2020
(This article belongs to the Special Issue Digital Audio Effects)
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. View Full-Text
Keywords: acoustic signal processing; audio systems; music; nonlinear systems; signal processing algorithms; supervised learning acoustic signal processing; audio systems; music; nonlinear systems; signal processing algorithms; supervised learning
Show Figures

Graphical abstract

MDPI and ACS Style

Wright, A.; Damskägg, E.-P.; Juvela, L.; Välimäki, V. Real-Time Guitar Amplifier Emulation with Deep Learning. Appl. Sci. 2020, 10, 766.

AMA Style

Wright A, Damskägg E-P, Juvela L, Välimäki V. Real-Time Guitar Amplifier Emulation with Deep Learning. Applied Sciences. 2020; 10(3):766.

Chicago/Turabian Style

Wright, Alec, Eero-Pekka Damskägg, Lauri Juvela, and Vesa Välimäki. 2020. "Real-Time Guitar Amplifier Emulation with Deep Learning" Applied Sciences 10, no. 3: 766.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Back to TopTop