Chirping up the Right Tree: Incorporating Biological Taxonomies into Deep Bioacoustic Classifiers
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 901-905
Abstract
Class imbalance in the training data hinders the generalization ability of machine listening systems. In the context of bioacoustics, this issue may be circumvented by aggregating species labels into super-groups of higher taxonomic rank: genus, family, order, and so forth. However, different applications of machine listening to wildlife monitoring may require different levels of granularity. This paper introduces TaxoNet, a deep neural network for structured classification of signals from living organisms. TaxoNet is trained as a multitask and multilabel model, following a new architectural principle in end-to-end learning named "hierarchical composition": shallow layers extract a shared representation to predict a root taxon, while deeper layers specialize recursively to lower-rank taxa. In this way, TaxoNet is capable of handling taxonomic uncertainty, out-of-vocabulary labels, and open-set deployment settings. An experimental benchmark on two new bioacoustic datasets (ANAFCC and BirdVox-14SD) leads to state-of-the-art results in bird species classification. Furthermore, on a task of coarse-grained classification, TaxoNet also outperforms a flat single-task model trained on aggregate labels.Keywords
This publication has 28 references indexed in Scilit:
- Towards the Automatic Classification of Avian Flight Calls for Bioacoustic MonitoringPLOS ONE, 2016
- Migratory birds under threatScience, 2016
- Visipedia circa 2015Pattern Recognition Letters, 2016
- Direct Mortality of Birds from Anthropogenic CausesAnnual Review of Ecology, Evolution, and Systematics, 2015
- A comprehensive phylogeny of birds (Aves) using targeted next-generation DNA sequencingNature, 2015
- Teaching with the Macaulay Library: An Online Archive of Animal Behavior RecordingsJournal of Microbiology & Biology Education, 2012
- The emerging significance of bioacoustics in animal species conservationBiological Conservation, 2010
- A survey of hierarchical classification across different application domainsData Mining and Knowledge Discovery, 2010
- Curriculum learning2009
- Phylogenetic and ecological effects on interspecific variation in structurally simple avian vocalizationsBiological Journal of the Linnean Society, 2008