Spatial Extrapolation of Early Room Impulse Responses with Noise-Robust Physics-Informed Neural Network

被引：0

作者：

Tsunokuni, Izumi ^{[1
]}

Sato, Gen ^{[1
]}

Ikeda, Yusuke ^{[1
]}

Oikawa, Yasuhiro ^{[2
]}

机构：

[1] Tokyo Denki Univ, Tokyo 1208551, Japan

[2] Waseda Univ, Tokyo 1698555, Japan

来源：

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES | 2024年 / E107A卷 / 09期

关键词：

deep neural network; wave equation; SIREN; PI-SIREN;

D O I：

10.1587/transfun.2024EAL2015

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper reports a spatial extrapolation of the sound field with a physics-informed neural network. We investigate the spatial extrapolation of the room impulse responses with physics-informed SIREN architecture. Furthermore, we proposed a noise-robust extrapolation method by introducing a tolerance term to the loss function.

引用

页码：1556 / 1560

页数：5

共 50 条

[1] Physics-Informed Time-Frequency Fusion Network With Attention for Noise-Robust Bearing Fault Diagnosis
Kim, Yejin
Kim, Young-Keun
IEEE ACCESS, 2024, 12 : 12517 - 12532
[2] Validation and extrapolation of atomic masses with a physics-informed fully connected neural network
Huang, Yiming
Chen, Jinhui
Jia, Jiangyong
Liu, Lu-Meng
Ma, Yu-Gang
Zhang, Chunjian
PHYSICAL REVIEW C, 2025, 111 (03)
[3] Physics-informed Neural Network for Force-free Magnetic Field Extrapolation
Zhang, Yao
Xu, Long
Yan, Yihua
RESEARCH IN ASTRONOMY AND ASTROPHYSICS, 2024, 24 (10)
[4] Physics-informed Neural Network for Force-free Magnetic Field Extrapolation
Yao Zhang
Long Xu
Yihua Yan
Research in Astronomy and Astrophysics, 2024, 24 (10) : 161 - 171
[5] A robust physics-informed neural network approach for predicting structural instability
Mai, Hau T.
Truong, Tam T.
Kang, Joowon
Mai, Dai D.
Lee, Jaehong
FINITE ELEMENTS IN ANALYSIS AND DESIGN, 2023, 216
[6] Robust Variational Physics-Informed Neural Networks
Rojas, Sergio
Maczuga, Pawel
Munoz-Matute, Judit
Pardo, David
Paszynski, Maciej
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 425
[7] Robust Variational Physics-Informed Neural Networks
Rojas, Sergio
Maczuga, Pawel
Muñoz-Matute, Judit
Pardo, David
Paszyński, Maciej
Computer Methods in Applied Mechanics and Engineering, 2024, 425
[8] Room impulse response reconstruction with physics-informed deep learning
Karakonstantis, Xenofon
Caviedes-Nozal, Diego
Richard, Antoine
Fernandez-Grande, Efren
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2024, 155 (02): : 1048 - 1059
[9] Extrapolation of cavitation and hydrodynamic pressure in lubricated contacts: a physics-informed neural network approach
Brumand-Poor, Faras
Azanledji, Freddy Kokou
Plueckhahn, Nils
Barlog, Florian
Boden, Lukas
Schmitz, Katharina
ADVANCED MODELING AND SIMULATION IN ENGINEERING SCIENCES, 2025, 12 (01)
[10] Physics informed neural network (PINN) for noise-robust phase-based magnetic resonance electrical properties tomography
Inda, Adan J. Garcia
Huang, Shao Y.
Immamoglu, Nevrez
Yu, Wenwei
2022 3RD URSI ATLANTIC AND ASIA PACIFIC RADIO SCIENCE MEETING (AT-AP-RASC), 2022,

← 1 2 3 4 5 →