Densely Connected CNNs for Bird Audio Detection

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.

Challenge solution source code available at https://github.com/topel/bird_audio_detection_challenge, Proc. EUSIPCO 2017

References in corpus (1)

• Striving for Simplicity: The All Convolutional Net

Cited by in corpus (5)

• Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challenge
• Robust sound event detection in bioacoustic sensor networks
• Multiscale CNN based Deep Metric Learning for Bioacoustic Classification: Overcoming Training Data Scarcity Using Dynamic Triplet Loss
• Deep Networks tag the location of bird vocalisations on audio spectrograms
• NIPS4Bplus: a richly annotated birdsong audio dataset