A Robust framework for sound event localization and detection on real recordings

TL;DR

This paper presents a robust ResNet-based framework for sound event localization and detection that leverages data augmentation, dataset mixing, and ensemble techniques to improve performance on real-world recordings.

Contribution

The authors introduce a comprehensive framework combining augmentation, dataset mixing, and ensemble methods to enhance SELD performance on real-world data.

Findings

Outperforms baseline methods in real-world sound recordings

Achieves competitive SELD performance

Effective use of augmentation and ensemble techniques

Abstract

This technical report describes the systems submitted to the DCASE2022 challenge task 3: sound event localization and detection (SELD). The task aims to detect occurrences of sound events and specify their class, furthermore estimate their position. Our system utilizes a ResNet-based model under a proposed robust framework for SELD. To guarantee the generalized performance on the real-world sound scenes, we design the total framework with augmentation techniques, a pipeline of mixing datasets from real-world sound scenes and emulations, and test time augmentation. Augmentation techniques and exploitation of external sound sources enable training diverse samples and keeping the opportunity to train the real-world context enough by maintaining the number of the real recording samples in the batch. In addition, we design a test time augmentation and a clustering-based model ensemble method to aggregate confident predictions. Experimental results show that the model under a proposed framework outperforms the baseline methods and achieves competitive performance in real-world sound recordings.