Haikubox review: High-tech birdwatching in the garden


For ornithologists, being able to identify birds by their song is the holy grail. Some people seem to be natural, hearing a song once and remembering it forever. If you’re like me – not one of those people – you’ve probably thought, “Why isn’t there a Shazam for birds?” Surely, if Shazam can identify a song with a few seconds of bad sound on turned off speakers, someone can figure out how to do the same for a bird singing clearly in a nearby tree.

That, in a nutshell, is what the creators of the Haikubox did: create the Birdsong Shazam.

That in itself is welcome and remarkable, but the Haikubox turns out to be so much more than that. It’s one of the few technologies that actually increases your connection to the world around you, rather than cutting you off.

Neural network

The bird migration started early this year. I know because my Haikubox told me. Not in so many words, but he started reporting the arrival of new warblers around mid-August, which means they’re already heading south to their wintering grounds in Central and South America.

With a full time job and three kids, I don’t have time to go out and go bird watching every day. I probably would have missed the Cape May warblers when they passed for a few weeks at the end of August. They never stay long and I always thought they got stuck in the birch glades a good mile up the road. Thanks to the Haikubox, I know that if they tend to spend their days elsewhere, they come to my house in the morning. I was able to see them because the Haikubox alerted me whenever it heard one.

That’s the magic of the Haikubox – it expands your world.

Photo: Haikubox

For something so remarkable, the Haikubox is decidedly prosaic in appearance. This is a 4 x 6 inch rounded square box about 2 inches thick. At the bottom is a sealed outlet for the power cord and a small microphone that records sounds around the Haikubox. While the device is weatherproof and I had no issues with it in the rain, the company recommends keeping it out of direct sunlight. Do not submerge it. Once you have a good location, plug it in and connect it to your Wi-Fi network via the Haikubox Connect app. The Haikubox will start recording audio 24/7.

That’s the end of the hardware, but that’s not where the magic really lies. Once connected to your wireless network, the Haikubox sends its recorded sounds to servers at the world-renowned Cornell Lab of Ornithology.

The Ornithology Lab has thousands of bird song samples and a neural network to process them. Neural networks are a form of machine learning software well suited to recognizing audio patterns – it’s how Siri and Google Assistant understand your voice. Similarly, the neural network can filter out birdsong from background noise. In order to find patterns, he must first learn what the pattern is. Cornell’s library of birdsong recordings provides the training the AI ​​needs to know which sounds are birdsong and which are watering your garden.

Cornell has been tweaking its neural network for some time. If you want to experience it without investing in a Haikubox, you can grab Cornell’s Merlin Bird ID app, which relies on a small subset of data and an AI processor similar to that used by the Haikubox. Haikubox creator David Mann told WIRED that Haikubox uses a modified version of BirdNet, called BirdNet for Haikubox.

Neither BirdNet nor BirdNet for Haikubox are perfect, but they are impressively accurate most of the time. Even better, you can use the Haikubox app to help the AI ​​improve.

Multiple views

Haikubox by Scott Gilbertson

To see which birds your Haikubox has heard and attempted to identify, you can use the Haikubox app for Android, iOS, or the web interface. The first time you open the app, you create an account, then you can log in through that account from any device. The data for each app is the same, and I’ve used all three in my testing. I found the mobile app more useful for notifications, but I preferred to browse and explore species information in the web app, as I could open eBird and other additional information in the back tabs -plan.


About Author

Comments are closed.