Recently, we have stumbled upon the massive efforts of the Bardnet research platform. BirdNET uses a neural network to detect birds through sound, and is a joint project between the Cornell Lab of Ornithology and Chemnitz University of Technology. What strikes us is that this project is impressively featured and accessible for a variety of applications. Undoubtedly, BirdNET’s goal is to become a one-stop shop for bird watching.
There are many ways that BirdNET can help you. Starting with perhaps the most popular option among us, we have iOS and Android apps – providing a feature for microphone-enabled “smart” devices in our pockets that even the most anti-app hackers can respect. However, the BirdNET team also talks about bringing sound recognition to our browsers, Raspberry Pi and other SBCs and even microcontrollers. We can’t wait for anyone to bring BirdNET to RP2040! Open-source code, models are freely available – there are very few uses that no one could cover with these.
About that raspberry pie version! There’s a sister project called BirdNET-Pi – an easy-to-install software package for the Raspberry Pi OS. After equipping your Pi with a USB sound card, you can record and analyze 24/7 using a “lite” version of BirdNET. Then, you’ll find a web interface where you’ll be able to log in and see marked bird sounds in real-time. Not only that – BirdNET-Pi processes words and creates spectrograms, puts the word into a database and can even send you notifications.
The BirdNET-Pi project is definitely open. Not only that – the BirdNET-Pi team insists everything should be completely local, unless you choose otherwise, and probably decide to share with others. Many make their BirdNET-Pi instances public and have a beautiful interactive map that shows the sounds of birds all over the world!
BirdNET is, without a doubt, a high-end project – and a shining example of what a dedicated research team can do with a neural network and an admirable goal in mind. For many of us who are happy to hear the sound of birds outside, it’s great to know that we can plug a USB sound card into our Pi and learn more about them – even if we still don’t recognize or see them. . We’ve covered bird sound recognition in microcontrollers before – also using machine learning.