The Oxford scientists tried to find out by designing a device called a \u201cbiologger\u201d that\u2019s attached to a lion\u2019s existing GPS collar to record audio and movement data. They then associated each call with a lion by cross-referencing the data through their recordings of roars.<\/p>\n
[Read: This AI system thinks we\u2019re getting better at wildlife conservation<\/a>]<\/em><\/p>\n Next, the team used the data collected by the biologgers to train a pattern recognition algorithm to recognize each lion\u2019s roar. Finally, they tested the algorithm on recordings it had not been fed before.<\/p>\n They found that each lion\u2019s roar produces a distinctive frequency shape. The algorithm used these to match a roar to an individual lion with 91.5% accuracy.<\/p>\n The system was developed by researchers from Oxford University\u2019s Department of Computer Science and WildCru, the conservation unit that had been tracking Cecil the Lion until he was killed by a trophy hunter in 2015<\/a>. His death sparked an outcry that forced the hunter into hiding.<\/p>\n Identifying the roars of other lions could help protect the roughly 20,000 of them<\/a> that are still left in the wild.<\/p>\n \u201cAfrican lion numbers are declining and developing cost-effective tools for monitoring, and ultimately better protecting, populations is a conservation priority,\u201d said WildCRU\u2019s Andrew J. Loveridge. \u201cThe ability to remotely evaluate the number of individual lions in a population from their roars could revolutionize the way in which lion populations are assessed.\u201d<\/p>\n You can read the full research paper in the journal Bioacoustics<\/a>.<\/p>\n Published October 14, 2020 \u2014 18:10 UTC <\/p>\n![](\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2020\/10\/Screenshot-2020-10-14-at-18.16.38.png\")