Wave Digital Filters and neural networks are two popular solutions for circuit modelling. In this presentation, we demonstrate a pipeline that makes use of our Differentiable Wave Digital Filters library. A dataset was collected from a diode clipper circuit and, with the library, was used to train a real-time deployable model. The trained model has higher accuracy and similar computation time when compared to traditional white-box models. We present this methodology to demonstrate the objective qualities and advantages of this approach.
IF YOU ARE ATTENDING ONLINE, ALL TALK SESSIONS CAN BE ACCESSED FROM THE MAIN LOBBY:
https://conference.audio.dev
