EquiSELD: Efficient training of equivariant sound event localization and detection networks

2026-09-19

AI Summary

研究提出EquiSELD网络，利用O(3)等变性处理FOA信号，提高声音事件定位与检测效率和性能，优于仅使用SO(3)等变性和非等变方法。

Abstract

First-order Ambisonics (FOA) signals exhibit exact O(3) symmetry: The rotation or reflection of the FOA signal modifies the direction of arrival of the sound sources, while preserving the sound sources themselves. Prior attempts to utilize this spatial symmetry of FOA to improve the efficiency and robustness of sound event detection and localization (SELD) systems either learned only an approximation of the symmetry through rotation-based augmentation or relied on computationally expensive methods to integrate equivariance. Furthermore, prior work focused exclusively on SO(3) equivariance , leaving the potential of incorporating O(3) equivariance for SELD tasks unclear. To address these limitations, we developed EquiSELD. This equivariant attention network processes first-order Ambisonics as paired streams of O(3)-invariant scalars and equivariant intensity vectors, producing an invariant activity magnitude and an equivariant DOA with a Multi-ACCDOA readout. To compare the impact of O(3) versus SO(3)-equivariance, we designed a matched SO(3)-only variant. EquiSELD outperforms prior equivariant networks on both simulated scenes with measured RIRs and recordings of real-world sound scenes at a fraction of the training cost. EquiSELD additionally surpasses the performance of non-equivariant SELD networks of a similar size on the simulated real-world sound scenes and achieves competitive performance on the real-world sound scenes.

Problem

• O(3) symmetry
• First-order Ambisonics
• Sound Event Localization and Detection
• equivariance
• efficiency

Innovation

• Equivariant
• O(3) Symmetry
• Sound Event Localization and Detection (SELD)
• First-Order Ambisonics (FOA)
• Efficient Training