Deep embedded clustering of coral reef bioacoustics
arXiv:2012.09982 · doi:10.1121/10.0004221
Abstract
Deep clustering was applied to unlabeled, automatically detected signals in a coral reef soundscape to distinguish fish pulse calls from segments of whale song. Deep embedded clustering (DEC) learned latent features and formed classification clusters using fixed-length power spectrograms of the signals. Handpicked spectral and temporal features were also extracted and clustered with Gaussian mixture models (GMM) and conventional clustering. DEC, GMM, and conventional clustering were tested on simulated datasets of fish pulse calls (fish) and whale song units (whale) with randomized bandwidth, duration, and SNR. Both GMM and DEC achieved high accuracy and identified clusters with fish, whale, and overlapping fish and whale signals. Conventional clustering methods had low accuracy in scenarios with unequal-sized clusters or overlapping signals. Fish and whale signals recorded near Hawaii in February-March 2020 were clustered with DEC, GMM, and conventional clustering. DEC features demonstrated the highest accuracy of 77.5% on a small, manually labeled dataset for classifying signals into fish and whale clusters.
arXiv commentto appear in Journal of the Acoustical Society of America, April 2021
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
- Machine learning in acoustics: theory and applications
- Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning
- Deep-learning source localization using multi-frequency magnitude-only data
- Performance of a Deep Neural Network at Detecting North Atlantic Right Whale Upcalls
- Compact representation of temporal processes in echosounder time series via matrix decomposition