Advancing sound field analysis with physics-informed neural networks

This work introduces a method that employs physics-informed neural networks to reconstruct sound fields in diverse rooms, including both typical acoustically damped meeting rooms and more spaces of cultural significance, such as concert halls or theatres. The neural network is trained using a limited set of room impulse responses, integrating the expressive capacity of neural networks with the fundamental physics of sound propagation governed by the wave equation. Consequently, the network accurately represents sound fields within an aperture without requiring extensive measurements, regardless of the complexity of the sound field. Notably, our approach extends beyond sound pressure estimation and includes valuable vectorial quantities, such as particle velocity and intensity, resembling classical holography methods. Experimental results confirm the efficacy of the proposed approach, underscoring its reconstruction accuracy and computational efficiency. Moreover, by enabling the acquisition of sound field quantities in the time domain, which were previously challenging to obtain from measurements, our method opens up new frontiers for the analysis and comprehension of sound propagation phenomena in rooms.