Sound propagation in realistic interactive 3D scenes with parameterized sources using deep neural operators

• 成果类型: Article
• 署名作者: Borrel-Jensen, Nikolas; Goswami, Somdatta; Engsig-Karup, Allan P.; Karniadakis, George Em; Jeong, Cheol-Ho
• 署名单位: Technical University of Denmark; Brown University; Technical University of Denmark; Brown University
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-13091
• DOI: 10.1073/pnas.2312159120
• 发表日期: 2024-01-09
• 关键词: universal approximation; nonlinear operators; domain; networks

摘要

We address the challenge of acoustic simulations in three-dimensional (3D) virtual rooms with parametric source positions, which have applications in virtual/augmented reality, game audio, and spatial computing. The wave equation can fully describe wave phenomena such as diffraction and interference. However, conventional numerical discretization methods are computationally expensive when simulating hundreds of source and receiver positions, making simulations with parametric source positions impractical. To overcome this limitation, we propose using deep operator networks to approximate linear wave-equation operators. This enables the rapid prediction of sound propagation in realistic 3D acoustic scenes with parametric source positions, achieving millisecond-scale computations. By learning a compact surrogate model, we avoid the offline calculation and storage of impulse responses for all relevant source/listener pairs. Our experiments, including various complex scene geometries, show good agreement with reference solutions, with root mean squared errors ranging from 0.02 to 0.10 Pa. Notably, our method signifies a paradigm shift as-to our knowledge-no prior machine learning approach has achieved precise predictions of complete wave fields within realistic domains.