Rock and blues guitar players prefer the use of vacuum-tube amplifiers due to the harmonic structures developed when the amplifiers are overdriven. The disadvantages of vacuum tubes compared against solid-state implementations, such as power consumption, reliability, cost, etc., are far outweighed by the desirable sound characteristics of the overdriven vacuum-tube amplifier. There are many approaches to modeling vacuum-tube amplifier behaviors in solid-state implementations. These include a variety of both analog and digital techniques, some of which are judged to be good approximations to the tube sound. In this paper we present early results of experiments in using a neural network to model the distortion produced by an overdriven vacuum-tube amplifier. Our approach is to use artificial neural networks of the recurrent variety, specifically a Nonlinear AutoRegressive eXogenous (NARX) network, to capture the nonlinear, dynamic characteristics of vacuum-tube amplifiers. NARX networks of various sizes have been trained on data sets consisting of samples of both sinusoidal and raw electric guitar signals and the amplified output of those signals applied to a tube-based amplifier driven at various levels of saturation. Models are evaluated using both quantitative (e.g., RMS error) and qualitative (listening tests) assessment methods on data sets that were not used in the network training. Listening tests- considered by us to be the most important evaluation method-at this point in the work, are indicative of the potential for success in the modeling of a vacuum-tube amplifier using a recurrent neural network.
[1]
Jyri Tapani Pakarinen,et al.
A Review of Digital Techniques for Modeling Vacuum-Tube Guitar Amplifiers
,
2009,
Computer Music Journal.
[2]
I. J. Leontaritis,et al.
Input-output parametric models for non-linear systems Part II: stochastic non-linear systems
,
1985
.
[3]
Kurt Hornik,et al.
Multilayer feedforward networks are universal approximators
,
1989,
Neural Networks.
[4]
Ah Chung Tsoi,et al.
FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling
,
1991,
Neural Computation.
[5]
Hava T. Siegelmann,et al.
Computational capabilities of recurrent NARX neural networks
,
1997,
IEEE Trans. Syst. Man Cybern. Part B.
[6]
David T. Yeh.
Automated Physical Modeling of Nonlinear Audio Circuits for Real-Time Audio Effects—Part II: BJT and Vacuum Tube Examples
,
2012,
IEEE Transactions on Audio, Speech, and Language Processing.
[7]
E. Barbour.
The cool sound of tubes [vacuum tube musical applications]
,
1998
.
[8]
Marco Gori,et al.
On the problem of local minima in recurrent neural networks
,
1994,
IEEE Trans. Neural Networks.
[9]
Martin A. Riedmiller,et al.
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
,
1993,
IEEE International Conference on Neural Networks.