Sirkku - Finnish Bird Identification App
Sirkku is a desktop application for identifying Finnish bird species from audio recordings. It runs entirely on your own computer: upload audio files and receive a CSV report of detected species, compatible with the BirdNET Analyzer format.
Download
A pre-release version is available for Windows and macOS (Apple Silicon). As this is an early testing release, the app is not yet code-signed, so your operating system may show a warning during installation.
About the Model
Bird identifications are produced by an AI model developed by doctoral researcher Patrik Lauha and collaborators in the research group led by Academy Professor Otso Ovaskainen at the University of Jyväskylä.
The model builds on the BirdNET convolutional neural network [1], extended and fine-tuned for Finnish species [2]. Training data includes passive acoustic recordings from Finnish field sites [3], recordings of Finnish bird species from the xeno-canto sound library [4], recordings collected by Harry Lehto, and recordings contributed by users of the Muuttolintujen Kevät -application.
Code Signing Policy
Free code signing for Windows provided by SignPath.io, certificate by SignPath Foundation.
Team roles and their members:
- Committers and reviewers: Members team
- Approvers: Owners
Privacy Policy
This program will not transfer any information to other networked systems. This program doesn't collect any personal information.
References
[1] Kahl, S., Wood, C. M., Eibl, M., & Klinck, H. (2021). BirdNET: A deep learning solution for avian diversity monitoring. Ecological Informatics, 61, 101236.
[2] Lauha, P., Somervuo, P., Lehikoinen, P., Geres, L., Richter, T., Seibold, S., & Ovaskainen, O. (2022). Domain‐specific neural networks improve automated bird sound recognition already with small amount of local data. Methods in Ecology and Evolution, 13(12), 2799-2810.
[3] Lehikoinen, P., Rannisto, M., Camargo, U., Aintila, A., Lauha, P., Piirainen, E., Somervuo, P. and Ovaskainen, O. (2023) A successful crowdsourcing approach for bird sound classification. Citizen Science: Theory and Practice, 8(1), 16.
[4] xeno-canto, xeno-canto foundation, https://www.xeno-canto.org