Interactive Neural Resonators

TL;DR

This paper introduces a neural network-based method for real-time, controllable synthesis of contact sounds using differentiable resonators, enabling intuitive interaction and novel sound creation.

Contribution

It presents a novel neural resonator approach with differentiable second-order resonators conditioned on physical parameters for interactive sound synthesis.

Findings

Enables real-time control of contact sounds

Allows for intuitive and dynamic sound manipulation

Demonstrates practical implementation and creative potential

Abstract

In this work, we propose a method for the controllable synthesis of real-time contact sounds using neural resonators. Previous works have used physically inspired statistical methods and physical modelling for object materials and excitation signals. Our method incorporates differentiable second-order resonators and estimates their coefficients using a neural network that is conditioned on physical parameters. This allows for interactive dynamic control and the generation of novel sounds in an intuitive manner. We demonstrate the practical implementation of our method and explore its potential creative applications.