discussion / Acoustics  / 22 March 2020

Prior work on Bird Flock identification

Hi there!

We have a project underway called "Identi-Flock" which is an ambitious attempt to port our individual pollinator identification software, www.withymbe.info over to identify flocks of birds. I say ambitious because we are dealing in DSP with aggregate noise-like signals, and need to filter real-world noises like human voices, aircraft in a much broader spectrum?

If anyone can offer any pointers, please, to prior work on flock audio identification, rather than individuals, I would be most grateful?

Tally ho!

Andrew.




Hi Harold,

Many thanks for this pointer; I have ordered the book "TinyML" from Amazon. This may offer an alternative to our previous approach which is based on individual identification? Worth a look?

All the best,

Andrew. :-)

Hi Andrew,

Dan here—I'm one of the authors of the TinyML book! I love your Withymbe project; I've previously done work involving embedded systems and insects, and it's interesting to hear about your plans for bird flocks.

As long as you have sufficient data, you should be able to identify different bird sounds and discern them from background noise. The TinyML book has a chapter that introduces the underlying techniques, and I'd also recommend taking a look at www.edgeimpulse.com - we've built a set of tools designed to make it easy to train these types of models.

We actually recently published a tutorial on Wildlabs about this very concept:

https://www.wildlabs.net/resources/case-studies/tutorial-train-tinyml-model-can-recognize-sounds-using-only-23-kb-ram

I'm always excited to learn about new applications; feel free to reach out if there's any way we can help. I'm [email protected].

Warmly,
Dan