Pre-processing spectrogram parameters improve the accuracy of bioacoustic classification using convolutional neural networks
2019
ABSTRACTA variety of automated classification approaches have been developed to extract species detection information from large
bioacousticdatasets. Convolutional neural networks (CNNs) are an image classification technique that can be operated on the
spectrogramof an audio recording. Using CNNs for
bioacousticclassification negates the need for sophisticated feature extraction techniques; however, CNNs may be sensitive to the parameters used to create
spectrograms. We used AlexNet to classify
spectrogramsof audio clips from 19 species of birdsong. We trained and tested AlexNet with the
spectrogramsand observed that mean classification accuracy ranged from 88.9% to 96.9% depending on the parameters used to create the
spectrogram. Classification accuracy was highest when we used a composite of four
spectrogramswith different combinations of scales for frequency and amplitude. Classification accuracy also varied depending on the FFT window size of the
spectrogram. Overall, our results suggest that op...
Keywords:
-
Correction
-
Source
-
Cite
-
Save
33
References
10
Citations
NaN
KQI