Physics-Aware Novel-View Acoustic Synthesis with Vision-Language Priors and 3D Acoustic Environment Modeling

Congyi Fan¹, Jian Guan^1*, Youtian Lin², Dongli Xu³, Tong Ye¹, Qiaoxi Zhu⁴, Pengming Feng⁵ Wenwu Wang⁶

Group of Intelligent Signal Processing, Harbin Engineering University, Harbin, China¹
School of Intelligence Science and Technology, Nanjing University, Suzhou, China²
Processing Speech and Images, KU Leuven, Leuven, Belgium³
Acoustics Lab, University of Technology Sydney, Ultimo, Australia⁴
State Key Laboratory of Space Information System and Integrated Application, Beijing, China⁵
Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK ^6
*Corresponding author