Improving Sound Event Detection In Domestic Environments Using Sound Separation
This work addresses sound event detection in domestic environments, offering an incremental improvement by integrating sound separation into existing detection pipelines.
The paper tackles the problem of overlapping sounds and noise in real-world sound event detection by using sound separation as a pre-processing step, resulting in improved detection performance with specific gains reported in metrics like F1-score.
Performing sound event detection on real-world recordings often implies dealing with overlapping target sound events and non-target sounds, also referred to as interference or noise. Until now these problems were mainly tackled at the classifier level. We propose to use sound separation as a pre-processing for sound event detection. In this paper we start from a sound separation model trained on the Free Universal Sound Separation dataset and the DCASE 2020 task 4 sound event detection baseline. We explore different methods to combine separated sound sources and the original mixture within the sound event detection. Furthermore, we investigate the impact of adapting the sound separation model to the sound event detection data on both the sound separation and the sound event detection.