Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses

TL;DR

This paper introduces a direction-aware neural field model that leverages Ambisonic RIRs to accurately interpolate and adapt to new room acoustics, capturing spatial and directional sound characteristics.

Contribution

The paper proposes DANF, a novel neural field that explicitly incorporates directional information from Ambisonic RIRs and introduces a direction-aware loss for improved sound field modeling.

Findings

DANF effectively captures spatial and directional sound properties.

The model demonstrates strong adaptability to new room environments.

Direction-aware loss improves the accuracy of RIR interpolation.

Abstract

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.