Download Constrained Pole Optimization for Modal Reverberation The problem of designing a modal reverberator to match a measured room impulse response is considered. The modal reverberator architecture expresses a room impulse response as a parallel combination of resonant filters, with the pole locations determined by the room resonances and decay rates, and the zeros by the source and listener positions. Our method first estimates the pole positions in a frequency-domain process involving a series of constrained pole position optimizations in overlapping frequency bands. With the pole locations in hand, the zeros are fit to the measured impulse response using least squares. Example optimizations for a mediumsized room show a good match between the measured and modeled room responses.
Download Neural Net Tube Models for Wave Digital Filters Herein, we demonstrate the use of neural nets towards simulating multiport nonlinearities inside a wave digital filter. We introduce a resolved wave definition which allows us to extract features from a Kirchhoff domain dataset and train our neural networks directly in the wave domain. A hyperparameter search is performed to minimize error and runtime complexity. To illustrate the method, we model a tube amplifier circuit inspired by the preamplifier stage of the Fender Pro-Junior guitar amplifier. We analyze the performance of our neural nets models by comparing their distortion characteristics and transconductances. Our results suggest that activation function selection has a significant effect on the distortion characteristic created by the neural net.
Download Aliasing Reduction in Neural Amp Modeling by Smoothing Activations The increasing demand for high-quality digital emulations of analog audio hardware, such as vintage tube guitar amplifiers, led
to numerous works on neural network-based black-box modeling,
with deep learning architectures like WaveNet showing promising
results. However, a key limitation in all of these models was the
aliasing artifacts stemming from nonlinear activation functions in
neural networks. In this paper, we investigated novel and modified activation functions aimed at mitigating aliasing within neural
amplifier models. Supporting this, we introduced a novel metric,
the Aliasing-to-Signal Ratio (ASR), which quantitatively assesses
the level of aliasing with high accuracy. Measuring also the conventional Error-to-Signal Ratio (ESR), we conducted studies on a
range of preexisting and modern activation functions with varying
stretch factors. Our findings confirmed that activation functions
with smoother curves tend to achieve lower ASR values, indicating a noticeable reduction in aliasing. Notably, this improvement
in aliasing reduction was achievable without a substantial increase
in ESR, demonstrating the potential for high modeling accuracy
with reduced aliasing in neural amp models.