@INPROCEEDINGS{Cramer:TaxoNet:ICASSP:2020,

  author={J. {Cramer} and V. {Lostanlen} and A. {Farnsworth} and J. {Salamon} and J. P. {Bello}},
  booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
 title={Chirping up the Right Tree: Incorporating Biological Taxonomies into Deep Bioacoustic Classifiers}, 
  year={2020},
  volume={},
  number={},
  pages={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={Acoustic signal detection;audio databases;classification algorithms;multilayer neural network;phylogeny},
  doi={10.1109/ICASSP40776.2020.9052908},
  ISSN={2379-190X},
  month={May},}