Sound field reconstruction in rooms with deep generative models

The characterisation of Room Impulse Responses over an extended region in a room by means of measurements requires dense spatial sampling with many microphones. This can often become intractable and time-consuming in practice. Well established reconstruction methods such as plane wave regression show that the sound field in a room can be reconstructed from sparsely distributed measurements. However, these reconstructions usually rely on assuming physical sparsity (i.e. few waves compose the sound field) or trait in the measured sound field, making the models less generalisable and problem-specific. In this paper, we introduce a method to reconstruct a sound field in an enclosure with the use of a Generative Adversarial Network (GAN), which synthesises new variants of the data distributions that it is trained upon. The proposed GAN model aims to estimate the underlying distribution of plane waves in any source free region and map these distributions from a stochastic, latent representation. A GAN is trained on a large number of synthesised sound fields represented by a random wave field and then tested on simulated sets of reverberant rooms.