A Physics-Informed Neural Network-Based Approach for the Spatial Upsampling of Spherical Microphone Arrays
This addresses the cost and complexity issue for audio engineers and researchers using spherical microphone arrays, but it is incremental as it builds on existing upsampling techniques with a neural network twist.
The paper tackles the problem of achieving high spatial resolution in spherical microphone arrays without requiring many expensive capsules by presenting a physics-informed neural network with Rowdy activation functions for spatial upsampling, and results show it outperforms a state-of-the-art signal processing method in its domain.
Spherical microphone arrays are convenient tools for capturing the spatial characteristics of a sound field. However, achieving superior spatial resolution requires arrays with numerous capsules, consequently leading to expensive devices. To address this issue, we present a method for spatially upsampling spherical microphone arrays with a limited number of capsules. Our approach exploits a physics-informed neural network with Rowdy activation functions, leveraging physical constraints to provide high-order microphone array signals, starting from low-order devices. Results show that, within its domain of application, our approach outperforms a state of the art method based on signal processing for spherical microphone arrays upsampling.