Paper Archive

In recent years, virtual analog modeling with neural networks experienced an increase in interest and popularity. Many different modeling approaches have been developed and successfully applied. In this paper we do not propose a novel model architecture, but rather address the problem of aliasing distortion introduced from nonlinearities of the modeled analog circuit. In particular, we propose to apply the general idea of antiderivative antialiasing to a state-trajectory network (STN). Applying antiderivative antialiasing to a stateful system in general leads to an integral of a multivariate function that can only be solved numerically, which is too costly for real-time application. However, an adapted STN can be trained to approximate the solution while being computationally efficient. It is shown that this approach can decrease aliasing distortion in the audioband significantly while only moderately oversampling the network in training and inference.

Download

We present a new onset detection algorithm which operates online in real time without delay. Our method incorporates a recurrent neural network to model the sequence of onsets based solely on causal audio signal information. Comparative performance against existing state-of-the-art online and offline algorithms was evaluated using a very large database. The new method – despite being an online algorithm – shows performance only slightly short of the best existing offline methods while outperforming standard approaches.

Download

Recent neural-based synthesis models have achieved impressive results for musical instrument sound generation. In particular, the Differentiable Digital Signal Processing (DDSP) framework enables the usage of spectral modeling analysis and synthesis techniques in fully differentiable architectures. Yet currently, it has only been used for modeling monophonic instruments. Leveraging the interpretability and modularity of this framework, the present work introduces a polyphonic differentiable model for piano sound synthesis, conditioned on Musical Instrument Digital Interface (MIDI) inputs. The model architecture is motivated by high-level acoustic modeling knowledge of the instrument which, in tandem with the sound structure priors inherent to the DDSP components, makes for a lightweight, interpretable and realistic sounding piano model. The proposed model has been evaluated in a listening test, demonstrating improved sound quality compared to a benchmark neural-based piano model, with significantly less parameters and even with reduced training data. The same listening test indicates that physical-modeling-based models still achieve better quality, but the differentiability of our lightened approach encourages its usage in other musical tasks dealing with polyphonic audio and symbolic data.

Download

In this paper, we address automating and systematizing the process of finding black-box models for virtual analogue audio effects with an optimal balance between error and latency. We introduce a multi-objective optimization approach based on hardware-aware neural architecture search which allows specifying the optimization balance of model error and latency according to the requirements of the application. By using a regularized evolutionary algorithm, it is able to navigate through a huge search space systematically. Additionally, we propose a search space for modelling non-linear dynamic audio effects consisting of over 41 trillion different WaveNet-style architectures. We evaluate its performance and usefulness by yielding highly effective architectures, either up to 18× faster or with a test loss of up to 56% less than the best performing models of the related work, while still showing a favourable trade-off. We can conclude that hardware-aware neural architecture search is a valuable tool that can help researchers and engineers developing virtual analogue models by automating the architecture design and saving time by avoiding manual search and evaluation through trial-and-error.

Download

In this paper we present a new method for the pseudo black-box modelling of general continuous-time state-space systems using a discrete-time state-space system with an embedded deep neural network. Examples are given of how this method can be applied to a number of common nonlinear electronic circuits used in music technology, namely two kinds of diode-based guitar distortion circuits and the lowpass filter of the Korg MS-20 synthesizer.

Download

The synchronization index model of sensory dissonance and roughness accounts for the degree of phase-locking to a particular frequency that is present in the neural patterns. Sensory dissonance (roughness) is defined as the energy of the relevant beating frequencies in the auditory channels with respect to the total energy. The model takes rate-code patterns at the level of the auditory nerve as input and outputs a sensory dissonance (roughness) value. The synchronization index model entails a straightforward visualization of the principles underlying sensory dissonance and roughness, in particular in terms of (i) roughness contributions with respect to cochlear mechanical filtering (on a Critical Band scale), and (ii) roughness contributions with respect to phase-locking synchrony (=the synchronization index for the relevant beating frequencies on a frequency scale). This paper presents the concept, and implementation of the synchronization index model and its application to musical scales.

Download

A supervised learning approach to ambience extraction from onechannel audio signals is presented. The extracted ambient signals are applied for the blind upmixing of musical audio recordings to surround sound formats. The input signal is processed by means of short-term spectral attenuation. The spectral weights are computed using a low-level feature extraction process and a neural network regression method. The multi-channel audio signal is generated by feeding the computed ambient signal into the rear channels of a surround sound system.

Download

Recent advancements in deep learning have shown great potential for audio applications, improving the accuracy of previous solutions for tasks such as music transcription, beat detection, and real-time audio processing. In addition, the availability of increasingly powerful embedded computers has led many deep learning framework developers to devise software optimized to run pretrained models in resource-constrained contexts. As a result, the use of deep learning on embedded devices and audio plugins has become more widespread. However, confusion has been rising around deep learning inference engines, regarding which of these can run in real-time and which are less resource-hungry. In this paper, we present a comparison of four available deep learning inference engines for real-time audio classification on the CPU of an embedded single-board computer: TensorFlow Lite, TorchScript, ONNX Runtime, and RTNeural. Results show that all inference engines can execute neural network models in real-time with appropriate code practices, but execution time varies between engines and models. Most importantly, we found that most of the less-specialized engines offer great flexibility and can be used effectively for real-time audio classification, with slightly better results than a real-time-specific approach. In contrast, more specialized solutions can offer a lightweight and minimalist alternative where less flexibility is needed.

Download

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

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