References of "Schmitz, Thomas"
     in
Bookmark and Share    
Full Text
See detailIntroducing a Dataset of Guitar Amplifier Sounds for Nonlinear Emulation Benchmarking
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

in 145th convention of audio engineering society (2018)

Recent progresses made in the nonlinear system identification field have improved the ability to emulate nonlinear audio systems such as tube guitar amplifiers. As a straightforward comparison of ... [more ▼]

Recent progresses made in the nonlinear system identification field have improved the ability to emulate nonlinear audio systems such as tube guitar amplifiers. As a straightforward comparison of different models cannot always be made, we propose a new reference dataset enabling to highlight the strengths and weaknesses of different nonlinear modeling methods. Our dataset gathers five different styles of guitar sounds passing through different guitar amplifiers with 10 steps of their gain parameter (i.e., the distortion level of the amplifier). Moreover, a Matlab function is also provided to obtain the desired input/output sounds in a matrix form. [less ▲]

Detailed reference viewed: 47 (13 ULiège)
Full Text
See detailNonlinear Real-Time Emulation of a Guitar Chain with Machine learning techniques
Schmitz, Thomas ULiege

Poster (2018, September 19)

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 ... [more ▼]

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. Recent progresses made in the nonlinear system identification field have improved the ability to emulate nonlinear audio systems such as tube guitar amplifiers. [less ▲]

Detailed reference viewed: 35 (1 ULiège)
Full Text
See detailComparison of Different Nonlinear Identification Methods: a Guitar Tube Amplifier Practical Case
Schmitz, Thomas ULiege

Scientific conference (2018, June 22)

Detailed reference viewed: 22 (2 ULiège)
Peer Reviewed
See detailNonlinear Real-Time Emulation of a Tube Amplifier with a Long Short Term Memory Neural-Network
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

Poster (2018, May 14)

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 ... [more ▼]

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%. [less ▲]

Detailed reference viewed: 66 (9 ULiège)
Peer Reviewed
See detailReal Time Emulation of Parametric Guitar Tube Amplifier with Long Short Term Memory Neural Network
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

in 4th International Conference on Image Processing and Pattern Recognition (IPPR 2018), Copenhagen, Denmark, April 28~29, 2018 (2018, April 28)

Numerous audio systems for musicians are expensive and bulky. Therefore, it could be advantageous to model them and to replace them by computer emulation. In guitar players’ world, audio systems could ... [more ▼]

Numerous audio systems for musicians are expensive and bulky. Therefore, it could be advantageous to model them and to replace them by computer emulation. In guitar players’ world, audio systems could have a desirable nonlinear behavior (distortion effects). It is thus difficult to find a simple model to emulate them in real time. Volterra series model and its subclass are usual ways to model nonlinear systems. Unfortunately, these systems are difficult to identify in an analytic way. In this paper we propose to take advantage of the new progress made in neural networks to emulate them in real time. We show that an accurate emulation can be reached with less than 1% of root mean square error between the signal coming from a tube amplifier and the output of the neural network. Moreover, the research has been extended to model the Gain parameter of the amplifier. [less ▲]

Detailed reference viewed: 36 (5 ULiège)
See detailNeural-Networks in Acoustics: a New Way to Solve Complex Acoustic Problems
Schmitz, Thomas ULiege

Conference (2018, March 18)

Detailed reference viewed: 17 (1 ULiège)
Full Text
Peer Reviewed
See detailHammerstein kernels identification by means of a sine sweep technique applied to nonlinear audio devices emulation
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

in Journal of the Audio Engineering Society (2017), 65(9), 696-710

Detailed reference viewed: 71 (9 ULiège)
Full Text
See detailA new toolbox for the identification of diagonal Volterra kernels allowing the emulation of nonlinear audio devices
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

in Schmitz, Thomas (Ed.) International Congress on Acoustics : ICA, Argentine 5-9 Septembre 2016 (2016, September 10)

Numerous audio systems are nonlinear. It is thus of great importance to study them and understand how they work. Volterra series model and its subclass (cascade Hammerstein-Wiener model) are usual ways to ... [more ▼]

Numerous audio systems are nonlinear. It is thus of great importance to study them and understand how they work. Volterra series model and its subclass (cascade Hammerstein-Wiener model) are usual ways to modelize nonlinear systems. However the identification methods of these models are still considered as an open topic. Therefore we have developed a new optimized identification tool ready for use and presented as a Matlab toolbox. This toolbox provides the parameters of the optimized sine sweep needed for the identification method, it is able to calculate the parameters of the Hammerstein model and to emulate the output signal of a nonlinear device for a given input signal. To evaluate the toolbox, we modelize a guitar distortion effect (the Tubescreamer) having a total harmonic distortion (THD) comprised in the range 10-23\%. We report a mean error of less than 0.7\% between the emulated signal and the signal coming from the distortion effect. [less ▲]

Detailed reference viewed: 107 (22 ULiège)
Full Text
See detailEmulate an analog nonlinear audio device, is it possible ?
Schmitz, Thomas ULiege

Conference (2016, January 25)

Non linear audio device emulation by means of Hammerstein model identification by sine sweep technique

Detailed reference viewed: 26 (4 ULiège)
Full Text
Peer Reviewed
See detailImprovement in non-linear guitar loudspeaker sound reproduction
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

in International Conference on Systems, Signals and Image Processing (2014, May)

This paper proposes a study of the accuracy of a guitar amplifier loudspeaker simulation. The simulation is based on a non-linear convolution of a signal using Volterra kernels, which are measured in ... [more ▼]

This paper proposes a study of the accuracy of a guitar amplifier loudspeaker simulation. The simulation is based on a non-linear convolution of a signal using Volterra kernels, which are measured in anechoic conditions with a sine-sweep technique. In this paper, we propose an evaluation of the method to minimise the cost in CPU load, while keeping the best performance in the sound reproduction. To assess the performance of the method, we measure errors between the simulated and real sounds. Human listening tests are moreover proposed in order to determine the minimum level of accuracy leading to unaudible differences with the real loudspeaker.. [less ▲]

Detailed reference viewed: 102 (20 ULiège)
Full Text
See detailModeling and analysis of nonlinear systems applied to a guitar chain signal
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

Conference (2014, February 21)

Detailed reference viewed: 63 (11 ULiège)
Full Text
See detailNonlinear guitar loudspeaker simulation
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

in Proceedings of the AES 134 th convention (2013, May)

Detailed reference viewed: 173 (27 ULiège)
Full Text
See detailNon-linear loudspeaker simulation. Guitar loudspeaker.
Schmitz, Thomas ULiege; Embrechts, Jean-Jacques ULiege

Conference (2012, June 06)

Detailed reference viewed: 412 (22 ULiège)