Journal
NEURAL COMPUTING & APPLICATIONS
Volume 32, Issue 4, Pages 915-927Publisher
SPRINGER LONDON LTD
DOI: 10.1007/s00521-018-3626-7
Keywords
Convolutional neural networks; Spectrograms; Short-time Fourier transform; Wavelets; Acoustic signal processing; Classification and detection
Categories
Funding
- AIMS CDT
- Royal Academy of Engineering
- Engineering and Physical Sciences Research Council [EP/L015897/1]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available