• Welcome to BirdForum, the internet's largest birding community with thousands of members from all over the world. The forums are dedicated to wild birds, birding, binoculars and equipment and all that goes with it.

    Please register for an account to take part in the discussions in the forum, post your pictures in the gallery and more.
ZEISS DTI thermal imaging cameras. For more discoveries at night, and during the day.

Warblr: an app that recognises birds from their song (1 Viewer)

xrxss15

Johannes
I am always having big trouble recognizing birds by their song (probably because I am completely non-musical). By pure chance I discovered that there is a project on kickstarter which aims on developing an app to help with that.

Maybe its interesting for you, too? They still need support to reach their goal of £50,000 by Mon, Dec 1 2014.

Regards,
Joh
 
I read about this app when the BBC did a story on it a couple of weeks back. It sounded like the technology is quite immature and there is still a lot of work to be done for it to be as useful as most users would want it to be. I'd love for there to be a Shazam for birds, I'm just not sure the technology is there yet, or whether it could even be done.
 
I'd love for there to be a Shazam for birds, I'm just not sure the technology is there yet, or whether it could even be done.

The Kickstarter project is to support the developing of the app. Its not a market-ready product yet. But if there are enough backers we might get one in the near future.
 
I am one of a small group of scientists and app developers working on an automatic ID for birdsongs. It has almost exactly the same aims as the kickstarter project, but we have the skills to make it ourselves so don't need to raise money. We are aiming for an early spring release date.

mathare is right, it is a very difficult thing to achieve, and it will probably be a long time until it is useful to anyone on this forum. However, we hope it will help to engage new people with the natural world around them.

The app will also have a more serious side. When a recording has been made, it will be possible to upload it, and it will be used in several ways. First, the recordings will be used to improve the app - the beauty of machine learning systems is that they improve as more data is added. Secondly, the recordings will be made available to reseachers. Subject to funding, they will be used in a collaboration between the Computer Science Department and the Ecosystems and Environment Research Centre at Salford University. Finally, verified data from the recordings will be used to add records to a national scheme such as iRecord or the NBN (in the UK).
 
Warning! This thread is more than 9 years ago old.
It's likely that no further discussion is required, in which case we recommend starting a new thread. If however you feel your response is required you can still do so.

Users who are viewing this thread

Back
Top