Efficient Sound Field Reconstruction with Conditional Invertible Neural Networks

TL;DR

This paper presents a novel approach using conditional invertible neural networks to efficiently reconstruct sound fields and room impulse responses, incorporating uncertainty estimates and reducing data requirements.

Contribution

The study introduces a CINN-based method for sound field reconstruction that balances accuracy and efficiency while handling uncertainties and sparse data.

Findings

Achieves accurate sound field reconstruction with less data.

Provides uncertainty estimates for sound field predictions.

Outperforms traditional Bayesian methods in efficiency.

Abstract

In this study, we introduce a method for estimating sound fields in reverberant environments using a conditional invertible neural network (CINN). Sound field reconstruction can be hindered by experimental errors, limited spatial data, model mismatches, and long inference times, leading to potentially flawed and prolonged characterizations. Further, the complexity of managing inherent uncertainties often escalates computational demands or is neglected in models. Our approach seeks to balance accuracy and computational efficiency, while incorporating uncertainty estimates to tailor reconstructions to specific needs. By training a CINN with Monte Carlo simulations of random wave fields, our method reduces the dependency on extensive datasets and enables inference from sparse experimental data. The CINN proves versatile at reconstructing Room Impulse Responses (RIRs), by acting either as a likelihood model for maximum a posteriori estimation or as an approximate posterior distribution through amortized Bayesian inference. Compared to traditional Bayesian methods, the CINN achieves similar accuracy with greater efficiency and without requiring its adaptation to distinct sound field conditions.