EcologybioRxiv
Towards interpretable learned representations for Ecoacoustics using variational auto-encoding
K. A. Gibb, A. Eldridge, C. J. Sandom, I. J. A. Simpson
This paper develops a variational auto-encoder to learn interpretable acoustic features from ecoacoustic data and demonstrates its ability to infer habitat degradation levels.
DOI 10.1016/j.ecoinf.2023.102449