Bayesian inference and neural estimation of acoustic wave propagation
This work addresses acoustic signal analysis for applications like relocalization, but it appears incremental as it builds on existing methods with new combinations.
The paper tackled the problem of analyzing acoustic signals by combining physics and machine learning to infer spectral acoustics characteristics and room impulse responses, achieving empirical validation on simulated data.
In this work, we introduce a novel framework which combines physics and machine learning methods to analyse acoustic signals. Three methods are developed for this task: a Bayesian inference approach for inferring the spectral acoustics characteristics, a neural-physical model which equips a neural network with forward and backward physical losses, and the non-linear least squares approach which serves as benchmark. The inferred propagation coefficient leads to the room impulse response (RIR) quantity which can be used for relocalisation with uncertainty. The simplicity and efficiency of this framework is empirically validated on simulated data.