Using deep learning to track time × frequency whistle contours of toothed whales without human-annotated training data
The Journal of the Acoustical Society of America · 2023
DOI: 10.1121/10.0020274 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, 2023. Verfasst von Pu Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, San Diego State University, San Diego, California 92182, USA. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Office of Naval Research.
Abstract (Originalsprache)
Many odontocetes produce whistles that feature characteristic contour shapes in spectrogram representations of their calls. Automatically extracting the time × frequency tracks of whistle contours has numerous subsequent applications, including species classification, identification, and density estimation. Deep-learning-based methods, which train models using analyst-annotated whistles, offer a promising way to reliably extract whistle contours. However, the application of such methods can be limited by the significant amount of time and labor required for analyst annotation. To overcome this challenge, a technique that learns from automatically generated pseudo-labels has been developed. These annotations are less accurate than those generated by human analysts but more cost-effective to generate. It is shown that standard training methods do not learn effective models from these pseudo-labels. An improved loss function designed to compensate for pseudo-label error that significantly increases whistle extraction performance is introduced. The experiments show that the developed technique performs well when trained with pseudo-labels generated by two different algorithms. Models trained with the generated pseudo-labels can extract whistles with an F1-score (the harmonic mean of precision and recall) of 86.31% and 87.2% for the two sets of pseudo-labels that are considered. This performance is competitive with a model trained with 12 539 expert-annotated whistles (F1-score of 87.47%).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, San Diego State University, San Diego, California 92182, USA.
- K. Lisa Yang Center for Conservation Bioacoustics, Cornell Laboratory of Ornithology, Cornell University, New York 14850, USA.
- Cooperative Institute for Marine and Atmospheric Research, Research Corporation of the University of Hawaii, Honolulu, Hawaii 96822, USA.
ORCID-Profile: Pu Li, Xiaobai Liu, Holger Klinck, Marie A Roch
Förderung
- Office of Naval Research
Zitieren
APA
Li, P., Liu, X., Klinck, H., Gruden, P., & Roch, M. A. (2023). Using deep learning to track time × frequency whistle contours of toothed whales without human-annotated training data. The Journal of the Acoustical Society of America. https://doi.org/10.1121/10.0020274
Vancouver
Li P, Liu X, Klinck H, Gruden P, Roch MA. Using deep learning to track time × frequency whistle contours of toothed whales without human-annotated training data. The Journal of the Acoustical Society of America. 2023. doi:10.1121/10.0020274
BibTeX
@article{Li2023,
author = {Li, Pu and Liu, Xiaobai and Klinck, Holger and Gruden, Pina and Roch, Marie A},
title = {Using deep learning to track time × frequency whistle contours of toothed whales without human-annotated training data},
journal = {The Journal of the Acoustical Society of America},
year = {2023},
doi = {10.1121/10.0020274}
}
EUVIMED