Communications of the ACM
Technology to Monitor Bird Sounds, Impacts of Environmental Change
This instrument is used by researchers at Oregon State University to monitor bird sounds in the forest, with technology far more effective than any available before.
Credit: Oregon State University
Oregon State University (OSU) researchers have developed a multi-instance, multi-label machine-learning system to simultaneously listen to multiple bird sounds. The system is designed to identify which species are present and how they might be changing as a result of habitat loss or climate change. The researchers say the system should provide an automated approach to ecological monitoring of bird species that is much more practical than human researchers sitting in the field.
"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," says OSU's Forrest Briggs.
The system also could be used to identify other forest noises besides bird sounds, and it could be utilized with other animal species, such as grasshoppers, crickets, frogs, and marine mammals. Briggs says the omnidirectional system's error rate is comparable to that achieved by human subjects, and notes that in one day of testing it generated 548 10-second recordings of sounds from 13 distinct bird species.
From Oregon State University News
View Full Article
Abstracts Copyright © 2012 Information Inc. 
, Bethesda, Maryland, USA
No entries found