Densely Connected CNNs for Bird Audio Detection

TL;DR

This paper evaluates various convolutional neural network architectures for bird audio detection, demonstrating that densely connected networks achieve the best performance in a competitive challenge setting.

Contribution

It introduces the effectiveness of DenseNets for bird sound detection and compares them with other CNN variants within a standardized challenge framework.

Findings

DenseNets achieved 88.22% AUC score.

Data augmentation and ensemble methods improved performance.

Enlarging training data with pseudo-labels degraded results.

Abstract

Detecting bird sounds in audio recordings automatically, if accurate enough, is expected to be of great help to the research community working in bio- and ecoacoustics, interested in monitoring biodiversity based on audio field recordings. To estimate how accurate the state-of-the-art machine learning approaches are, the Bird Audio Detection challenge involving large audio datasets was recently organized. In this paper, experiments using several types of convolutional neural networks (i.e. standard CNNs, residual nets and densely connected nets) are reported in the framework of this challenge. DenseNets were the preferred solution since they were the best performing and most compact models, leading to a 88.22% area under the receiver operator curve score on the test set of the challenge. Performance gains were obtained thank to data augmentation through time and frequency shifting, model parameter averaging during training and ensemble methods using the geometric mean. On the contrary, the attempts to enlarge the training dataset with samples of the test set with automatic predictions used as pseudo-groundtruth labels consistently degraded performance.