Learning Acoustic Scattering Fields for Highly Dynamic Interactive Sound Propagation

We present a novel hybrid sound propagation algorithm for interactive applications. Our approach is designed for general dynamic scenes and uses a neural network-based learned scattered field representation along with ray tracing to generate specular, diffuse, diffraction, and occlusion effects efficiently. To handle general objects, we exploit properties of the acoustic scattering field and use geometric deep learning to approximate the field using spherical harmonics. We use a large dataset for training, and compare its accuracy with the ground truth generated using an accurate wave-based solver. The additional overhead of computing the learned scattered field at runtime is small and we highlight the interactive performance by generating plausible sound effects in dynamic scenes with diffraction and occlusion effects. We demonstrate the perceptual benefits of our approach based on an audio-visual user study.