Gradient-based Optimisation of Modulation Effects
This work addresses the need for efficient and low-latency digital emulation of analog modulation effects for audio processing applications, but it is incremental as it builds on previous differentiable digital signal processing methods.
The paper tackled the problem of emulating analog modulation effects like flangers, chorus, and phasers using machine learning, achieving results where the model's sound output was sometimes perceptually indistinguishable from analog references, though challenges persisted for effects with long delay times and feedback.
Modulation effects such as phasers, flangers and chorus effects are heavily used in conjunction with the electric guitar. Machine learning based emulation of analog modulation units has been investigated in recent years, but most methods have either been limited to one class of effect or suffer from a high computational cost or latency compared to canonical digital implementations. Here, we build on previous work and present a framework for modelling flanger, chorus and phaser effects based on differentiable digital signal processing. The model is trained in the time-frequency domain, but at inference operates in the time-domain, requiring zero latency. We investigate the challenges associated with gradient-based optimisation of such effects, and show that low-frequency weighting of loss functions avoids convergence to local minima when learning delay times. We show that when trained against analog effects units, sound output from the model is in some cases perceptually indistinguishable from the reference, but challenges still remain for effects with long delay times and feedback.