Anuran call synthesis with diffusion models for enhanced bioacoustic classification under data scarcity

Anuran call synthesis with diffusion models for enhanced bioacoustic classification under data scarcity

Addressing data scarcity in anuran bioacoustic monitoring, this study introduces diffusion probabilistic models (DPMs) for generating realistic calls and demonstrates their efficacy in data augmentation. A DPM framework combined with FID-based selection ensured synthetic call quality, with initial r...

Full description

Saved in:
Bibliographic Details
Main Authors: José Sebastián Ñungo Manrique, Francisco Gómez, Freddy Hernández-Romero
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Anura bioacoustics
Diffusion generative models
Audio generation
Data augmentation
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125003310
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

http://www.sciencedirect.com/science/article/pii/S1574954125003310

Similar Items