Bioacoustic detection with wavelet-conditioned convolutional neural networks

Many real-world time series analysis problems are characterized by low signal-to-noise ratios and compounded by scarce data. Solutions to these types of problems often rely on handcrafted features extracted in the time or frequency domain. Recent high-profile advances in deep learning have improved...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2020-02, Vol.32 (4), p.915-927
Main Authors: Kiskin, Ivan, Zilli, Davide, Li, Yunpeng, Sinka, Marianne, Willis, Kathy, Roberts, Stephen
Format: Article
Language:English
Subjects:
Acoustic noise
Artificial Intelligence
Artificial neural networks
Birds
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Datasets
Deep learning
Depth profiling
Feature extraction
Fourier transforms
Image Processing and Computer Vision
Machine learning
Neural networks
Probability and Statistics in Computer Science
S.I. : Deep learning for music and audio
Species classification
Time series
Wavelet analysis
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many real-world time series analysis problems are characterized by low signal-to-noise ratios and compounded by scarce data. Solutions to these types of problems often rely on handcrafted features extracted in the time or frequency domain. Recent high-profile advances in deep learning have improved performance across many application domains; however, they typically rely on large data sets that may not always be available. This paper presents an application of deep learning for acoustic event detection in a challenging, data-scarce, real-world problem. We show that convolutional neural networks (CNNs), operating on wavelet transformations of audio recordings, demonstrate superior performance over conventional classifiers that utilize handcrafted features. Our key result is that wavelet transformations offer a clear benefit over the more commonly used short-time Fourier transform. Furthermore, we show that features, handcrafted for a particular dataset, do not generalize well to other datasets. Conversely, CNNs trained on generic features are able to achieve comparable results across multiple datasets, along with outperforming human labellers. We present our results on the application of both detecting the presence of mosquitoes and the classification of bird species.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-018-3626-7