Nonlinear Real-Time Emulation of a Tube Amplifier with a Long Short Time Memory Neural-Network
×
Cite This
Citation & Abstract
T. Schmitz, and J. Embrechts, "Nonlinear Real-Time Emulation of a Tube Amplifier with a Long Short Time Memory Neural-Network," Paper 9966, (2018 May.). doi:
T. Schmitz, and J. Embrechts, "Nonlinear Real-Time Emulation of a Tube Amplifier with a Long Short Time Memory Neural-Network," Paper 9966, (2018 May.). doi:
Abstract: Numerous audio systems for musicians are expensive and bulky. Therefore, it could be advantageous to model them and to replace them by computer emulation. Their nonlinear behavior requires the use of complex models. We propose to take advantage of the progress made in the field of machine learning to build a new model for such nonlinear audio devices (such as the tube amplifier). This paper specially focuses on the real-time constraints of the model. Modifying the structure of the Long Short Term Memory neural-network has led to a model 10 times faster while keeping a very good accuracy. Indeed, the root mean square error between the signal coming from the tube amplifier and the output of the neural network is around 2%.
@article{schmitz2018nonlinear,
author={schmitz, thomas and embrechts, jean-jacques},
journal={journal of the audio engineering society},
title={nonlinear real-time emulation of a tube amplifier with a long short time memory neural-network},
year={2018},
volume={},
number={},
pages={},
doi={},
month={may},}
@article{schmitz2018nonlinear,
author={schmitz, thomas and embrechts, jean-jacques},
journal={journal of the audio engineering society},
title={nonlinear real-time emulation of a tube amplifier with a long short time memory neural-network},
year={2018},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={numerous audio systems for musicians are expensive and bulky. therefore, it could be advantageous to model them and to replace them by computer emulation. their nonlinear behavior requires the use of complex models. we propose to take advantage of the progress made in the field of machine learning to build a new model for such nonlinear audio devices (such as the tube amplifier). this paper specially focuses on the real-time constraints of the model. modifying the structure of the long short term memory neural-network has led to a model 10 times faster while keeping a very good accuracy. indeed, the root mean square error between the signal coming from the tube amplifier and the output of the neural network is around 2%.},}
TY - paper
TI - Nonlinear Real-Time Emulation of a Tube Amplifier with a Long Short Time Memory Neural-Network
SP -
EP -
AU - Schmitz, Thomas
AU - Embrechts, Jean-Jacques
PY - 2018
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2018
TY - paper
TI - Nonlinear Real-Time Emulation of a Tube Amplifier with a Long Short Time Memory Neural-Network
SP -
EP -
AU - Schmitz, Thomas
AU - Embrechts, Jean-Jacques
PY - 2018
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2018
AB - Numerous audio systems for musicians are expensive and bulky. Therefore, it could be advantageous to model them and to replace them by computer emulation. Their nonlinear behavior requires the use of complex models. We propose to take advantage of the progress made in the field of machine learning to build a new model for such nonlinear audio devices (such as the tube amplifier). This paper specially focuses on the real-time constraints of the model. Modifying the structure of the Long Short Term Memory neural-network has led to a model 10 times faster while keeping a very good accuracy. Indeed, the root mean square error between the signal coming from the tube amplifier and the output of the neural network is around 2%.
Numerous audio systems for musicians are expensive and bulky. Therefore, it could be advantageous to model them and to replace them by computer emulation. Their nonlinear behavior requires the use of complex models. We propose to take advantage of the progress made in the field of machine learning to build a new model for such nonlinear audio devices (such as the tube amplifier). This paper specially focuses on the real-time constraints of the model. Modifying the structure of the Long Short Term Memory neural-network has led to a model 10 times faster while keeping a very good accuracy. Indeed, the root mean square error between the signal coming from the tube amplifier and the output of the neural network is around 2%.
Authors:
Schmitz, Thomas; Embrechts, Jean-Jacques
Affiliation:
University of Liege, Liege, Belgium
AES Convention:
144 (May 2018)
Paper Number:
9966
Publication Date:
May 14, 2018Import into BibTeX
Subject:
Posters: Modeling
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=19483