Search papers, labs, and topics across Lattice.
This paper introduces EscFOA, a geometry-aware spatial audio generation framework that enhances spatial learning for visually impaired learners by providing acoustic scaffolding in immersive 360-degree educational environments. By combining 3D Gaussian Splatting with conditional diffusion models, EscFOA reconstructs scene geometry from 360-degree videos to produce high-fidelity spatial audio that aligns with the environmental structure. The results show that EscFOA significantly improves spatial orientation and reduces cognitive load compared to traditional audio methods, demonstrating its potential to facilitate inclusive access to complex learning materials for visually impaired individuals.
Geometry-consistent generative audio can dramatically enhance spatial learning for visually impaired learners, outperforming traditional audio methods in immersive educational settings.
Immersive 360-degree educational environments often lack accessible spatial structure, limiting visually impaired learners'ability to orient, explore, and construct mental representations. This paper proposes EscFOA, a geometry-aware spatial audio generation framework designed as an \emph{acoustic scaffolding} to support spatial cognition. By integrating 3D Gaussian Splatting (3DGS) with conditional diffusion models, EscFOA reconstructs scene geometry from 360-degree videos to synthesize high-fidelity spatial audio consistent with the environmental structure. Explicitly targeting learning outcomes like independent spatial orientation and reduced cognitive load, EscFOA significantly outperforms conventional monaural and stereo audio in supporting spatial learning behaviors among blindfolded sighted participants (simulating visually impaired learners). These findings demonstrate that geometry-consistent generative audio can effectively enable inclusive access to complex spatial learning materials.
