Warblr : 'Shazam for birds' app lets you identify birdsong in real-time

Home »Warblr : 'Shazam for birds' app lets you identify birdsong in real-time

Warblr : 'Shazam for birds' app lets you identify birdsong in real-time

Posted by sciencetech-blog on Wednesday, October 29, 2014 Label:

comments

Just in time for spring, scientists hope to launch a 'Shazam for birds' that will help people identify the tweets that are waking them up in the morning.

The app, dubbed Warblr, claims to be able to recognise the song of 88 bird species, and could help track their migration patterns.

Like Shazam, it works by recording nearby noises on smartphones to analyse it in real-time and identify the bird species according to its tweets.

Just in time for spring, scientists hope to launch a 'Shazam for birds' that will help people find out which birds are waking you up in the morning. The app, dubbed Warblr, claims to be able to recognise the song of 88 bird species, and could help track their migration patterns

Whenever the app identifies a bird, geo-tracking allows it to map which species is being spotted where and when, with the information made public.

The information will be made publicly available to allow zoologists and ecologists monitor species growth and decline, as well as patterns of migration.

The app, developed by two scientists using a grant from Queen Mary University of London, is currently raising funding for development on Kickstarter.

At the time of writing, the campaign has raised £3,290 ($5,300) towards its £50,000 ($80,570) goal.

Whenever the app identifies a bird, geo-tracking allows it to map which species are being spotted where and when, with the information made public. Pictured on the left is a bluethroat and on the right a bee eater

After recording the bird song, the app returns a list of the most likely results, with percentage indicating their levels of likelihood.

However, initial test with the BBC found that the app still needs to iron out some problems. For instance, Warblr struggled to distinguish between a canada goose and screaming child.

CROW OR RAVEN? TWITCHER APP ANALYSES YOUR BIRD PHOTOS

It's not uncommon to see a pretty bird flit by when you are enjoying a walk or a picnic - even if you live in a built-up area.

But if your knowledge of flying fauna isn't up to Bill Oddie's standards, it can be difficult to work out which creature you have spotted. But now an app, developed by computer scientists, can identify a bird from a single photo.

A team of researchers led by Professor Peter Belhumeur at Columbia Engineering, New York City, have used computer vision and machine learning techniques to create Birdsnap.

The free iPhone app claims to be an electronic field guide featuring 500 of the most common North American bird species.

It lets users identify bird species by uploading photos and there is also a website, which includes 50,000 images as well as bird calls for each species.

Beginners and experts can sort through species alphabetically, by their relationship in the Tree of Life and by the frequency with which they are sighted at a particular place and season.

In the first test, the app recorded a canada goose, but interference from a 'screaming child' caused the app to misidentify the calls as those of a crow.

The Kickstarter funding, according to the team, is to help address the app's problems which will be sold in the spring for £1.99 ($3.20).

Creator, Florence Wilkinson says her goal is 'to bring people closer to the natural world through technology' and help protect the wildlife for the future.

In the first test, the app recorded a canada goose, but interference from a 'screaming child' caused the app to misidentify the calls as those of a crow

The app, developed by two scientists using a grant from Queen Mary University of London, is currently raising funding for development on Kickstarter. At the time of writing, the campaign has raised £3,290 ($5,300) towards its £50,000 ($80,570) goal

Put the internet to work for you.

Turn off or edit this Recipe

sciencetech-blog