Realistic sound is essential in virtual environments, such as computer games and mixed reality. Efficient and accurate numerical methods for pre-calculating acoustics have been developed over the last decade; however, pre-calculating acoustics makes handling dynamic scenes with moving sources challenging, requiring intractable memory storage. A physics-informed neural network (PINN) method in 1D is presented, which learns a compact and efficient surrogate model with parameterized moving Gaussian sources and impedance boundaries, and satisfies a system of coupled equations. The model shows relative mean errors below 2%/0.2 dB and proposes a first step in developing PINNs for realistic 3D scenes.

翻译：虚拟环境（如计算机游戏与混合现实）中，真实感声音至关重要。过去十年间，高效精确的声学预计算数值方法已得到发展；然而，声学预计算使处理包含移动声源的动态场景面临挑战，需要难以承受的存储开销。本文提出一种一维物理信息神经网络（PINN）方法，该方法学习一个紧凑高效的替代模型，其可处理参数化移动高斯声源与阻抗边界，并满足一组耦合方程。模型相对平均误差低于2%/0.2 dB，为开发面向真实三维场景的PINN迈出了第一步。