Semiautomated generation of species-specific training data from large, unlabeled acoustic datasets for deep supervised birdsong isolation
Overall, we show that site-specific DSSS is a promising upstream solution for wildlife audio analysis tools that break down in the presence of background noise. By training on site-specific data, our method is robust to unique, site-specific interference that caused previous methods to fail.
Authors
- Timothy H. Keitt (ORCID: https://orcid.org/0000-0002-4587-1083)
- Andrea Contina (ORCID: https://orcid.org/0000-0002-0484-6711)
- David P. Knobles (ORCID: https://orcid.org/0000-0001-8555-742X)
- Preston S. Wilson (ORCID: https://orcid.org/0000-0002-4420-7180)
- Brendan Allison
- Justin Sasek
Institutions
- The University of Texas Rio Grande Valley (US)
- Walker (United States) (US)
- The University of Texas at Austin (US)
Publication Details
- Journal
- PeerJ
- Published
- 2024-09-23
- DOI
- https://doi.org/10.7717/peerj.17854
- Citations
- 5
- Primary Topic
- Animal Vocal Communication and Behavior
- Type
- article
- Field-Weighted Citation Impact
- 2.55
Funders
- National Science Foundation
- University of Texas at Austin