picture of a brambling (a small bird), with "BirdNET-Pi" written above it

Neural Network Identifies Bird Calls, Even On Your Pi

June 25, 2022 by Arya Voronova 20 Comments

Recently, we’ve stumbled upon the extensive effort that is the BirdNET research platform. BirdNET uses a neural network to identify birds by the sounds they make, and is a joint project between the Cornell Lab of Ornithology and the Chemnitz University of Technology. What strikes us is – this project is impressively featureful and accessible for a variety of applications. No doubt, BirdNET is aiming to become a one-stop shop for identifying birds as they sing.

There’s plenty of ways BirdNET can help you. Starting with likely the most popular option among us, there are iOS and Android apps – giving the microphone-enabled “smart” devices in our pockets a feature even the most app-averse 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 someone to bring BirdNET to a RP2040! The code’s open-source, the models are freely available – there’s hardly a use case one couldn’t cover with these.

About that Raspberry Pi version! There’s a sister project called BirdNET-Pi – it’s an easy-to-install software package intended for the Raspberry Pi OS. Having equipped your Pi with a USB sound card, you can make it do 24/7 recording and analysis using a “lite” version of BirdNET. Then, you get a web interface you can log into and see bird sounds identified in real-time. Not just that – BirdNET-Pi also processes the sounds and creates spectrograms, keeps the sound in a database, and can even send you notifications.

The BirdNET-Pi project is open, too, of course. Not just that – the BirdNET-Pi team emphasizes everything being fully local, unless you choose otherwise, and perhaps decide to share it with others. Many do make their BirdNET-Pi instances public, and there’s a lovely interactive map that shows bird sounds all across the world!

BirdNET is, undoubtedly, a high-effort 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 feel joy when we hear birds outside, it’s endearing to know that we can plug a USB sound card into our Pi and learn more about them – even if we can’t spot them or recognize them by sight just yet. We’ve covered bird sound recognition on microcontrollers before – also using machine learning.

A bird-shaped yellow PCB with legs wound out of wire, perched on its creator's arm. The bird has a lot of through-hole components on it, as well as an assortment of different-colored LEDs.

Printed Circuit Bird Family Calls For Us To Consider Analog

January 23, 2022 by Arya Voronova 16 Comments

On our favourite low-attention-span content site, [Kelly Heaton] has recently started sharing a series of “Printed Circuit Birds”. These are PCBs shaped like birds, looking like birds and chirping like birds – and they are fully analog! The sound is produced by a network of oscillators feeding into each other, and, once tuned, is hardly distinguishable from the bird songs you might hear outside your window. Care and love was put into making this bird life-like – it perches on Kelly’s arm with legs woven out of single-strand wire and talons made out of THT resistors, in the exact same way you would expect a regular bird to sit on your arm – that is, if you ever get lucky enough. It’s not just one bird – there’s a family of circuit animals, including a goose, a crow and even a cricket.

Why did these animals came to life – metaphorically, but also, literally? There must be more to a non-ordinary project like this, and we asked Kelly about it. These birds are part of her project to explore models of consciousness in ways that we typically don’t employ. Our habit is to approach complex problems in digital domains, but we tend to miss out on elegance and simplicity that analog circuits are capable of. After all, even our conventional understanding of a neural network is a matrix of analog coefficients that we then tune, a primitive imitation of how we assume human brains to work – and it’s this “analog” approach that has lately moved us ever so closer to reproducing “intelligence” in a computer.

Kelly’s work takes a concept that would have many of us get the digital toolkit, and makes it wonderfully life-like using a small bouquet of simple parts. It’s a challenge to our beliefs and approaches, compelling in its grace, urging us to consider and respect analog circuits more when it comes to modelling consciousness and behaviours. If it’s this simple to model sounds and behaviour of a biological organism, a task that’d have us writing DSP and math code to replicate on a microcontroller – what else are we missing from our models?

Kelly has more PCBs to arrive soon in preparation for her NYC exhibit in February, and will surely be posting updates on her Twitter page! We’ve covered her work before, and if you haven’t seen it yet, her Supercon 2019 talk on Electronic Naturalism would be a great place to start! Such projects tend to inspire fellow hackers to build other non-conventional projects, and this chirping pendant follows closely in Kelly’s footsteps! The direction of this venture reminds us a lot of BEAM robotics, which we’ve recently reminisced upon as something that’s impacted generations of hackers to look at electronics we create through an entirely different lens.

Continue reading “Printed Circuit Bird Family Calls For Us To Consider Analog” →