Deep Learning for Tube Amplifier Emulation

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.

[1]  Jyri Tapani Pakarinen,et al.  A Review of Digital Techniques for Modeling Vacuum-Tube Guitar Amplifiers , 2009, Computer Music Journal.

[2]  Thomas Schmitz,et al.  Nonlinear Real-Time Emulation of a Tube Amplifier with a Long Short Time Memory Neural-Network , 2018 .

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  David L. Livingston,et al.  A vacuum-tube guitar amplifier model using a recurrent neural network , 2013, 2013 Proceedings of IEEE Southeastcon.

[5]  Xavier Serra,et al.  A Wavenet for Speech Denoising , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[7]  Thomas Hélie,et al.  Volterra Series and State Transformation for Real-Time Simulations of Audio Circuits Including Saturations: Application to the Moog Ladder Filter , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[8]  Michael J. Kemp.  Analysis and Simulation of Non-Linear Audio Processes Using Finite Impulse Responses Derived at Multiple Impulse Amplitudes , 1999 .

[9]  Udo Zölzer,et al.  BLACK-BOX MODELING OF DISTORTION CIRCUITS WITH BLOCK-ORIENTED MODELS Conference , 2016 .

[10]  Adam Coates,et al.  Deep Voice: Real-time Neural Text-to-Speech , 2017, ICML.

[11]  Lamberto Tronchin.  The Emulation of Nonlinear Time-Invariant Audio Systems with Memory by Means of Volterra Series , 2013 .

[12]  Daniel P. W. Ellis,et al.  General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline , 2018, DCASE.

[13]  David T. Yeh,et al.  Digital implementation of musical distortion circuits by analysis and simulation , 2009 .

[14]  Angelo Farina,et al.  EMULATION OF NOT-LINEAR, TIME-VARIANT DEVICES BY THE CONVOLUTION TECHNIQUE , 2005 .

[15]  Thomas S. Huang,et al.  Fast Generation for Convolutional Autoregressive Models , 2017, ICLR.

[16]  Xavier Serra,et al.  Freesound technical demo , 2013, ACM Multimedia.

[17]  Kurt James Werner,et al.  The Fender Bassman 5F6-A Family of Preamplifier Circuits—A Wave Digital Filter Case Study , 2016 .

[18]  David L. Livingston,et al.  A Vacuum-Tube Guitar Amplifier Model Using Long/Short-Term Memory Networks , 2018, SoutheastCon 2018.

[19]  Simone Orcioni,et al.  Identification of Volterra Models of Tube Audio Devices using Multiple-Variance Method , 2018, Journal of the Audio Engineering Society.

[20]  E. Barbour.  The cool sound of tubes [vacuum tube musical applications] , 1998 .

[21]  Udo Zölzer,et al.  BLOCK-ORIENTED GRAY BOXMODELING OF GUITAR AMPLIFIERS , 2017 .

[22]  Vesa Välimäki,et al.  Virtual Analog Effects , 2011 .

[23]  Matti Karjalainen,et al.  Wave Digital Simulation of a Vacuum-Tube Amplifier , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[24]  Michael Schoeffler,et al.  webMUSHRA — A Comprehensive Framework for Web-based Listening Tests , 2018 .