Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses
This work addresses the challenge of capturing precise directional audio characteristics for applications in virtual reality or acoustics, representing an incremental improvement over prior neural field methods.
The paper tackles the problem of accurately representing directional sound fields from limited measurements by proposing a direction-aware neural field (DANF) that incorporates Ambisonic-format room impulse responses, achieving improved interpolation with a direction-aware loss and adaptation techniques like low-rank adaptation.
The characteristics of a sound field are intrinsically linked to the geometric and spatial properties of the environment surrounding a sound source and a listener. The physics of sound propagation is captured in a time-domain signal known as a room impulse response (RIR). Prior work using neural fields (NFs) has allowed learning spatially-continuous representations of RIRs from finite RIR measurements. However, previous NF-based methods have focused on monaural omnidirectional or at most binaural listeners, which does not precisely capture the directional characteristics of a real sound field at a single point. We propose a direction-aware neural field (DANF) that more explicitly incorporates the directional information by Ambisonic-format RIRs. While DANF inherently captures spatial relations between sources and listeners, we further propose a direction-aware loss. In addition, we investigate the ability of DANF to adapt to new rooms in various ways including low-rank adaptation.