SSL-Net: A Synergistic Spectral and Learning-based Network for Efficient Bird Sound Classification

TL;DR

SSL-Net is a novel framework that combines spectral and learned features for efficient bird sound classification, reducing the need for extensive labeled data and customized models, and demonstrating high accuracy with limited samples.

Contribution

The paper introduces SSL-Net, a general framework that effectively fuses spectral and learned features, along with three feature fusion strategies, for improved bird sound classification.

Findings

High classification accuracy on a standard bird audio dataset.

Effective feature extraction with limited labeled samples.

Quantitative analysis of three feature fusion strategies.

Abstract

Efficient and accurate bird sound classification is of important for ecology, habitat protection and scientific research, as it plays a central role in monitoring the distribution and abundance of species. However, prevailing methods typically demand extensively labeled audio datasets and have highly customized frameworks, imposing substantial computational and annotation loads. In this study, we present an efficient and general framework called SSL-Net, which combines spectral and learned features to identify different bird sounds. Encouraging empirical results gleaned from a standard field-collected bird audio dataset validate the efficacy of our method in extracting features efficiently and achieving heightened performance in bird sound classification, even when working with limited sample sizes. Furthermore, we present three feature fusion strategies, aiding engineers and researchers in their selection through quantitative analysis.