Physics-Informed Machine Learning for Sound Field Estimation: Fundamentals, state of the art, and challenges [Special Issue On Model-Based and Data-Driven Audio …

S Koyama, JGC Ribeiro, T Nakamura… - IEEE Signal …, 2025 - ieeexplore.ieee.org
The area of study concerning the estimation of spatial sound, ie, the distribution of a physical
quantity of sound such as acoustic pressure, is called sound field estimation, which is the …

Physics-informed machine learning for sound field estimation

S Koyama, JGC Ribeiro, T Nakamura, N Ueno… - arxiv preprint arxiv …, 2024 - arxiv.org
The area of study concerning the estimation of spatial sound, ie, the distribution of a physical
quantity of sound such as acoustic pressure, is called sound field estimation, which is the …

A Zero-Shot Physics-Informed Dictionary Learning Approach for Sound Field Reconstruction

S Damiano, F Miotello, M Pezzoli, A Bernardini… - arxiv preprint arxiv …, 2024 - arxiv.org
Sound field reconstruction aims to estimate pressure fields in areas lacking direct
measurements. Existing techniques often rely on strong assumptions or face challenges …

A physics-informed neural network-based approach for the spatial upsampling of spherical microphone arrays

F Miotello, F Terminiello, M Pezzoli… - … on Acoustic Signal …, 2024 - ieeexplore.ieee.org
Spherical microphone arrays are convenient tools for capturing the spatial characteristics of
a sound field. However, achieving superior spatial resolution requires arrays with numerous …

Sound field estimation using deep kernel learning regularized by the wave equation

D Sundström, S Koyama… - 2024 18th International …, 2024 - ieeexplore.ieee.org
In this work, we introduce a spatio-temporal kernel for Gaussian process (GP) regression-
based sound field estimation. Notably, GPs have the attractive property that the sound field …

Point neuron learning: a new physics-informed neural network architecture

H Bi, TD Abhayapala - EURASIP Journal on Audio, Speech, and Music …, 2024 - Springer
Abstract Machine learning and neural networks have advanced numerous research
domains, but challenges such as large training data requirements and inconsistent model …

A broadband modeling method for range-independent underwater acoustic channels using physics-informed neural networks

Z Huang, L An, Y Ye, X Wang, H Cao, Y Du… - The Journal of the …, 2024 - pubs.aip.org
Accurate broadband modeling of underwater acoustic channels is vital for underwater
acoustic detection, localization, and communication. Conventional modeling methodologies …

Reconstruction of directional sources using physics-informed neural networks

E Morena, R Malvermi, M Pezzoli… - INTER-NOISE and …, 2024 - ingentaconnect.com
In the context of augmented/virtual reality applications, replicating the directivity of sound
sources is a critical step to ensure a high-quality immersive experience. However, accurate …

[PDF][PDF] Milestone M7 Review and results validation on all cabin noise control system–decision on integration strategy WP2–Noise reduction in vehicle and aircraft …

A Hense, M Ahi, C Liang, CK Lai - in-nova-horizon.eu
The IN-NOVA project is dedicated to develop and provide knowledge and solutions in the
field of noise reduction. Specifically, it aims to develop innovative and effective methods of …

[PDF][PDF] Attentive Convolutional Network for Far-field Sound Reconstruction using Near-field Measurement

C Liang, F Ripamonti, HR Karimi - researchgate.net
The far field refers to the acoustic region far from the sound source, however, accurate
measurement of the far-field sound often requires an appropriate placement of mics and …