Echo-aware Adaptation of Sound Event Localization and Detection in Unknown Environments
This addresses robustness for audio-based detection systems in varied real-world settings, but it is incremental as it builds on domain adaptation methods.
The paper tackles the problem of sound event localization and detection (SELD) systems degrading in unknown environments due to reverberation and noise, proposing echo-aware feature refinement (EAR) that uses acoustic echoes to suppress environmental effects, with experiments on the FOA-MEIR dataset showing effective performance improvements.
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.