Download A general-purpose deep learning approach to model time-varying audio effects Audio processors whose parameters are modified periodically over time are often referred as time-varying or modulation based audio effects. Most existing methods for modeling these type of effect units are often optimized to a very specific circuit and cannot be efficiently generalized to other time-varying effects. Based on convolutional and recurrent neural networks, we propose a deep learning architecture for generic black-box modeling of audio processors with long-term memory. We explore the capabilities of deep neural networks to learn such long temporal dependencies and we show the network modeling various linear and nonlinear, time-varying and time-invariant audio effects. In order to measure the performance of the model, we propose an objective metric based on the psychoacoustics of modulation frequency perception. We also analyze what the model is actually learning and how the given task is accomplished.
Download Anti-Aliasing of Neural Distortion Effects via Model Fine Tuning Neural networks have become ubiquitous with guitar distortion
effects modelling in recent years. Despite their ability to yield
perceptually convincing models, they are susceptible to frequency
aliasing when driven by high frequency and high gain inputs.
Nonlinear activation functions create both the desired harmonic
distortion and unwanted aliasing distortion as the bandwidth of
the signal is expanded beyond the Nyquist frequency. Here, we
present a method for reducing aliasing in neural models via a
teacher-student fine tuning approach, where the teacher is a pretrained model with its weights frozen, and the student is a copy of
this with learnable parameters. The student is fine-tuned against
an aliasing-free dataset generated by passing sinusoids through
the original model and removing non-harmonic components from
the output spectra.
Our results show that this method significantly suppresses aliasing for both long-short-term-memory networks (LSTM) and temporal convolutional networks (TCN). In the
majority of our case studies, the reduction in aliasing was greater
than that achieved by two times oversampling. One side-effect
of the proposed method is that harmonic distortion components
are also affected.
This adverse effect was found to be modeldependent, with the LSTM models giving the best balance between
anti-aliasing and preserving the perceived similarity to an analog
reference device.
Download RT-WDF — A Modular Wave Digital Filter Library with Support for Arbitrary Topologies and Multiple Nonlinearities Wave Digital Filters (WDF) [1] are a popular approach for virtual analog modeling [2]. They provide a computationally efficient way to simulate lumped physical systems with well-studied numerical properties. Recent work by Werner et al. [3, 4] enables the use of WDFs to model systems with complicated topologies and multiple/multiport nonlinearities, to a degree not previously known. We present an efficient, portable, modular, and open-source C++ library for real time Wave Digital Filter modeling: RT-WDF [5]. The library allows a WDF to be specified in an object-oriented tree with the same structure as a WDF tree and implements the most recent advances in the field. We give an architectural overview and introduce the main concepts of operation on three separate case studies: a switchable attenuator, the Bassman tone stack, and a common-cathode triode amplifier. It is further shown how to expand the existent set of non-linear models to encourage custom extensions. Index Terms— wave digital filter, software, real time, virtual analog modeling, multiple nonlinearities
Download Modelling digital musical effects for signal processors, based on real effect manifestation analysis For quite some time in the area of commercial utilization of digital audio effects, efforts have emerged to create simulate by software analog effects and effect processors This paper deals with the analysis of musical effects, the design of algorithms for simulating these effects, and their realization on both digital signal processors and the PC platform in the form of plug-in modules for the DirectX environment. It also deals with the problem of controlling the effect parameters and with subjective testing of algorithms, and it examines the fidelity of simulated effects as compared with the original.
Download Exposure Bias and State Matching in Recurrent Neural Network Virtual Analog Models Virtual analog (VA) modeling using neural networks (NNs) has
great potential for rapidly producing high-fidelity models. Recurrent neural networks (RNNs) are especially appealing for VA due
to their connection with discrete nodal analysis. Furthermore, VA
models based on NNs can be trained efficiently by directly exposing them to the circuit states in a gray-box fashion. However,
exposure to ground truth information during training can leave the
models susceptible to error accumulation in a free-running mode,
also known as “exposure bias” in machine learning literature. This
paper presents a unified framework for treating the previously
proposed state trajectory network (STN) and gated recurrent unit
(GRU) networks as special cases of discrete nodal analysis. We
propose a novel circuit state-matching mechanism for the GRU
and experimentally compare the previously mentioned networks
for their performance in state matching, during training, and in exposure bias, during inference. Experimental results from modeling
a diode clipper show that all the tested models exhibit some exposure bias, which can be mitigated by truncated backpropagation
through time. Furthermore, the proposed state matching mechanism improves the GRU modeling performance of an overdrive
pedal and a phaser pedal, especially in the presence of external
modulation, apparent in a phaser circuit.
Download The Influence of Small Variations in a Simplified Guitar Amplifier Model A strongly simplified guitar amplifier model, consisting of four stages, is presented. The exponential sweep technique is used to measure the frequency dependent harmonic spectra. The influence of small variations of the system parameters on the harmonic components is analyzed. The differences of the spectra are explained and visualized.
Download A Physical Model of the Trombone Using Dynamic Grids for Finite-Difference Schemes In this paper, a complete simulation of a trombone using finitedifference time-domain (FDTD) methods is proposed. In particular, we propose the use of a novel method to dynamically vary the
number of grid points associated to the FDTD method, to simulate
the fact that the physical dimension of the trombone’s resonator
dynamically varies over time. We describe the different elements
of the model and present the results of a real-time simulation.
Download Interpolation Filters for Antiderivative Antialiasing Aliasing is an inherent problem in nonlinear digital audio processing which results in undesirable audible artefacts. Antiderivative antialiasing has proved to be an effective approach to mitigate aliasing distortion, and is based on continuous-time convolution of a linearly interpolated distorted signal with antialiasing filter kernels. However, the performance of this method is determined by the properties of interpolation filter. In this work, cubic interpolation kernels for antiderivative antialiasing are considered. For memoryless nonlinearities, aliasing reduction is improved employing cubic interpolation. For stateful systems, numerical simulation and stability analysis with respect to different interpolation kernels remain in favour of linear interpolation.
Download Examining the Oscillator Waveform Animation Effect An enhancing effect that can be applied to analogue oscillators in subtractive synthesizers is termed Animation, which is an efficient way to create a sound of many closely detuned oscillators playing in unison. This is often referred to as a supersaw oscillator. This paper first explains the operating principle of this effect using a combination of additive and frequency modulation synthesis. The Fourier series will be derived and results will be presented to demonstrate its accuracy. This will then provide new insights into how other more general waveform animation processors can be designed.
Download Harmonic Instability of Digital Soft Clipping Algorithms In this paper several different digital soft clipping algorithms are described and analysed. It is discussed how the quality of each algorithm can be estimated. A testing methodology is devised to show the levels of nonlinearities produced as a function of the input signal amplitude. It is proposed that, while all soft clipping algorithms produce higher order nonlinearities, the instability of the produced harmonics plays a crucial role in the transparency of the effect. Existing and novel clipping algorithms are thus compared and classified based on their measured properties, including total harmonic distortion and inter-modulation distortion estimates. This paper proposes a conclusion related to the quality and properties of different algorithms.