Echo-aware Adaptation of Sound Event Localization and Detection in Unknown Environments

TL;DR

This paper introduces echo-aware feature refinement (EAR) for sound event localization and detection, enhancing robustness in unknown environments by leveraging acoustic echoes to suppress environmental effects at the feature level.

Contribution

The study proposes a novel EAR method that uses spatial cues from acoustic echoes to improve SELD performance in unseen environments, addressing a key challenge in domain adaptation.

Findings

EAR improves SELD accuracy in unknown environments

FOA-MEIR dataset validates the effectiveness of EAR

Environmental effects are suppressed at the feature level

Abstract

Our goal is to develop a sound event localization and detection (SELD) system that works robustly in unknown environments. A SELD system trained on known environment data is degraded in an unknown environment due to environmental effects such as reverberation and noise not contained in the training data. Previous studies on related tasks have shown that domain adaptation methods are effective when data on the environment in which the system will be used is available even without labels. However adaptation to unknown environments remains a difficult task. In this study, we propose echo-aware feature refinement (EAR) for SELD, which suppresses environmental effects at the feature level by using additional spatial cues of the unknown environment obtained through measuring acoustic echoes. FOA-MEIR, an impulse response dataset containing over 100 environments, was recorded to validate the proposed method. Experiments on FOA-MEIR show that the EAR effectively improves SELD performance in unknown environments.