A Shazam for birds? Scientists develop birdsong identifier.
Researchers have developed a technology to identify a species of bird by its song, even among many other birdsongs.
Steve Zack/Wildlife Conservation Society/AP
If you walk through a forest, you might hear a chorus of tweets. But with all that racket, how can you know precisely who is serenading your stroll?
Like the mobile app Shazam, which can name a tune just by listening to it, a new technology could soon help you to identify a bird species by its chirps.
Computer scientists at the Queen Mary University of London have devised a system that automatically identifies a bird by its song, even among many distracting voices of other feathered fliers.
"Automatic classification of bird sounds is useful when trying to understand how many and what type of birds you might have in one location," said study lead author Dan Stowell in a news release.
The researchers designed an automatic analysis technique and classification algorithm to identify many bird species, selecting their individual songs from among the cacophonous twittering in crowded treetops.
Existing birdsong recordings from the British Sound Library Archive and online sources gave the researchers plenty of data on which to test their system. Their work was published this week in the journal PeerJ.
Although it sounds complicated, this automated program won’t be just for professional ornithologists. The researchers say amateur birders could find this technology helpful too.
This system could also answer questions about our own species' chirps and warbles. "Birdsong has a lot in common with human language, even though it evolved separately," said Dr. Stowell in the news release. "For example, many songbirds go through similar stages of vocal learning as we do, as they grow up, which makes them interesting to study."
Because of these similarities, “we can understand more about how human language evolved and social organisation in animal groups," said Stowell in the news release. "The attraction of fully automatic analysis is that we can create a really large evidence base to address these big questions."
But the researchers haven’t limited themselves to these questions. They also aim to classify forests’ choruses in much more detail.
Stowell said in the news release, "I'm working on techniques that can transcribe all the bird sounds in an audio scene: not just who is talking, but when, in response to whom, and what relationships are reflected in the sound, for example who is dominating the conversation."