Physics-Informed Machine Learning For Sound Field Estimation

TL;DR

This paper explores physics-informed machine learning techniques to improve sound field estimation by integrating physical sound properties into data-driven models, enhancing accuracy over traditional methods.

Contribution

It introduces the fundamentals of physics-informed machine learning for sound field estimation and reviews current PIML-based approaches, emphasizing the importance of physical properties.

Findings

PIML improves sound field estimation accuracy.

Physical properties enhance machine learning models.

Overview of current PIML methods for sound fields.

Abstract

The area of study concerning the estimation of spatial sound, i.e., the distribution of a physical quantity of sound such as acoustic pressure, is called sound field estimation, which is the basis for various applied technologies related to spatial audio processing. The sound field estimation problem is formulated as a function interpolation problem in machine learning in a simplified scenario. However, high estimation performance cannot be expected by simply applying general interpolation techniques that rely only on data. The physical properties of sound fields are useful a priori information, and it is considered extremely important to incorporate them into the estimation. In this article, we introduce the fundamentals of physics-informed machine learning (PIML) for sound field estimation and overview current PIML-based sound field estimation methods.