Name
Abstract | ||
|---|---|---|
Many real-world time-series analysis problems are characterised by scarce data. Solutions typically rely on hand-crafted features extracted from the time or frequency domain allied with classification or regression engines which condition on this (often low-dimensional) feature vector. The huge advances enjoyed by many application domains in recent years have been fuelled by the use of deep learning architectures trained on large data sets. This paper presents an application of deep learning for acoustic event detection in a challenging, data-scarce, real-world problem. Our candidate challenge is to accurately detect the presence of a mosquito from its acoustic signature. We develop convolutional neural networks (CNNs) operating on wavelet transformations of audio recordings. Furthermore, we interrogate the networku0027s predictive power by visualising statistics of network-excitatory samples. These visualisations offer a deep insight into the relative informativeness of components in the detection problem. We include comparisons with conventional classifiers, conditioned on both hand-tuned and generic features, to stress the strength of automatic deep feature learning. Detection is achieved with performance metrics significantly surpassing those of existing algorithmic methods, as well as marginally exceeding those attained by individual human experts. |
Year | Venue | Field |
|---|---|---|
2017 | arXiv: Machine Learning | Frequency domain,Feature vector,Convolutional neural network,Acoustic signature,Artificial intelligence,Deep learning,Artificial neural network,Feature learning,Mathematics,Machine learning,Wavelet |
DocType | Volume | Citations |
Journal | abs/1705.05180 | 0 |
PageRank | References | Authors |
0.34 | 5 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ivan Kiskin | 1 | 1 | 3.09 |
| Bernardo Pérez Orozco | 2 | 0 | 0.68 |
| Theo Windebank | 3 | 0 | 0.34 |
| Davide Zilli | 4 | 1 | 2.08 |
| Marianne Sinka | 5 | 0 | 2.03 |
| katherine j willis | 6 | 0 | 2.37 |
| stephen j roberts | 7 | 1244 | 174.70 |