If you've ever sat in a wooded area and listened to the birds, you may have notices that there's a multitude of sounds including different types of songs by different species coming from different locations. It can be a challenge to pick out who is where doing what even to the most seasoned bird song experts. So field researchers trying to understand how different species are doing need as much help as they can get. Researchers at Oregon State University have just such a tool -- a new technology that allows multiple bird songs recorded at once to be picked apart with better accuracy than ever before.
PhysOrg states, "The system, one of the first of its type, should provide an automated approach to ecological monitoring of bird species that is much more practical than a human sitting in the field, hours on end."The researchers think that the technology can not only work for birds, bu for many forest sounds including species like insects and frogs, and perhaps even marine mammals. But for now, studying birds is the focus, as is working out the kinks in the technology. It currently has the same error rate as human experts, and can experience interference from other noises like rain. Still, the usefulness of the technology can't be understated.
Those changes in bird behavior and appearance can signal all sorts of things, from how they're reacting to changes in their habitat such as human presence or shifts due to climate change -- and what kind of changes that area might experience from a loss of bird species as they help with pollination and spreading seeds.
"Birds are important in themselves, but also an early warning system of larger changes taking place in the environment," Forrest Briggs, a doctoral student in computer science at OSU, says in the article. "Now we can tell down to the second when a bird arrives, leaves, when and where it's choosing to nest, that type of information. It's just not practical to do that with human monitoring."