advertisement

Ithaca, NY—Hear a bird singing? Today with the free Merlin Bird ID app from the Cornell Lab of Ornithology, you can make a quantum leap in bird identification just by holding up your phone. As Merlin listens with you it uses AI technology to identify each species like magic, displaying in real time a list and photos of the birds that are singing or calling.

Merlin can now help you identify more than 400 bird species by sound throughout the United States and Canada (with more species and regions to come), adding to features that already enable you to identify 7,500 species around the world based on your bird photos or descriptions. 

Merlin’s pioneering approach to sound identification uses AI technology powered by tens of thousands of citizen scientists who contributed their bird observations and sound recordings to the Lab’s Macaulay Library via eBird, the Cornell Lab’s global database.

https://yubanet.com/wp-content/uploads/2021/06/Annas-Hummingbird-by-Brian-Sullivan_Macaulay-Library-at-the-Cornell-Lab-of-Ornithology.mp4
Anna’s Hummingbird by Brian Sullivan_Macaulay Library at the Cornell Lab of Ornithology

“Thousands of sound recordings train Merlin to recognize each bird species, and more than a billion bird observations in eBird tell Merlin which birds are likely to be present at a particular place and time,” says Drew Weber, Merlin project coordinator. “Having this incredibly robust bird dataset—and feeding that into faster and more powerful machine-learning tools—enables Merlin to ID birds by sound now, when doing so seemed like a daunting challenge just a few years ago.” 

Rather than cracking the problem by teaching computers to identify the actual sounds, researchers at the Cornell Lab trained Merlin to recognize the visual patterns of each bird song based on spectrograms—images that capture the amplitude, frequency, and duration of the sound. They had previously used visual techniques to successfully train Merlin to identify birds in photos.

“The sound recordings that each user makes get quickly turned into spectrograms—and in the same way Merlin can identify a bird by what it looks like, it can now also now make an ID by what the bird’s sound looks like,” says Grant Van Horn, lead researcher for Merlin.

Merlin helps identify individual bird sounds even when multiple birds are singing at the same time. After you record sounds, you can select a species and zip back to the spot in the recording where its song or call occurred. The recordings are saved automatically so you can listen to and look at the sounds again and again, making Merlin a great learning tool.

With one-touch access, you can also go deeper and learn more about each bird with ID tips, maps, and more than 80,000 photos and sounds from the Cornell Lab’s Macaulay Library.

Common Yellowthroat by Brad Imhoff_Macaulay Library at the Cornell Lab of Ornithology

“The Merlin app really unlocks a whole new world of sound,” said the Cornell Lab’s Jessie Barry, whose team led the project. She adds, “It helps everyone solve the mystery birds they’re hearing around them, and the technology that powers Merlin sound identification can also be used for research and conservation, opening up new possibilities for the way scientists can monitor, study, and protect birds.”

The Merlin Bird ID app with the new Sound ID feature is available for free on iOS and Android devices. First released in 2014 and downloaded by more than 6 million people worldwide, Merlin is the most accurate and global bird ID app available, and the only one enabling both sound and photo identification powered by AI.