Queen Mary University of London (QMUL) researchers have developed a successful way of identifying bird sounds from large audio collections.
Their method takes advantage of large datasets of sound recordings provided by the British Library Sound Archive and online sources such as the Xeno Canto. The researchers say the strategy integrates feature-learning and a classification algorithm to establish a system capable of differentiating between which birds are present in a large dataset.
"Automatic classification of bird sounds is useful when trying to understand how many and what type of birds you might have in one location," says QMUL researcher Dan Stowell.
The new classification system performed well in a public contest using a set of thousands of recordings with more than 500 bird species from Brazil. The system was rated as the best performing audio-only classifier, and placed second out of all the entries.
"I'm working on techniques that can transcribe all the bird sounds in an audio scene: not just who is talking, but when, in response to whom, and what relationships are reflected in the sound, for example who is dominating the conversation," Stowell says.
From Queen Mary, University of London
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA