Channel-Spatial-Based Few-Shot Bird Sound Event Detection

TL;DR

This paper introduces a novel few-shot learning model for bird sound event detection that leverages channel and spatial attention mechanisms to improve detection accuracy with limited training data.

Contribution

It proposes the Metric Channel-Spatial Network with a Channel Spatial Squeeze-Excitation block, enhancing feature learning for few-shot bird sound detection.

Findings

Achieved an F-measure of 66.84% on DCASE 2022 Take5 dataset

Attained a PSDS of 58.98% on the same dataset

Demonstrated the effectiveness of attention mechanisms in few-shot bird sound detection

Abstract

In this paper, we propose a model for bird sound event detection that focuses on a small number of training samples within the everyday long-tail distribution. As a result, we investigate bird sound detection using the few-shot learning paradigm. By integrating channel and spatial attention mechanisms, improved feature representations can be learned from few-shot training datasets. We develop a Metric Channel-Spatial Network model by incorporating a Channel Spatial Squeeze-Excitation block into the prototype network, combining it with these attention mechanisms. We evaluate the Metric Channel Spatial Network model on the DCASE 2022 Take5 dataset benchmark, achieving an F-measure of 66.84% and a PSDS of 58.98%. Our experiment demonstrates that the combination of channel and spatial attention mechanisms effectively enhances the performance of bird sound classification and detection.