Forwarded to me (Dan Dugan):
Scientists from Queen Mary University of London have found a successful way=
of identifying bird sounds from large audio collections, which could be us=
eful for expert and amateur bird-watchers alike.
The analysis used recordings of individual birds and of dawn choruses to id=
entify characteristics of bird sounds. It took advantage of large datasets =
of sound recordings provided by the British Library Sound Archive, and onli=
ne sources such as the Dutch archive called Xeno Canto.
Publishing in the journal PeerJ, the authors describe an approach that comb=
ines feature-learning -- an automatic analysis technique -- and a classific=
ation algorithm, to create a system that can distinguish between which bird=
s are present in a large dataset.
"Automatic classification of bird sounds is useful when trying to understan=
d how many and what type of birds you might have in one location," commente=
d lead author Dr Dan Stowell from QMUL's School of Electronic Engineering a=
nd Computer Science and Centre for Digital Music.
Dr Stowell was recently awarded a five-year fellowship from the Engineering=
and Physical Sciences Research Council (EPSRC) to develop computerised pro=
cesses to detect multiple bird sounds in large sets of audio recordings.
"Birdsong has a lot in common with human language, even though it evolved s=
eparately. For example, many songbirds go through similar stages of vocal l=
earning as we do, as they grow up, which makes them interesting to study. F=
rom them we can understand more about how human language evolved and social=
organisation in animal groups," said Dr Stowell.
He added: "The attraction of fully automatic analysis is that we can create=
a really large evidence base to address these big questions."
The classification system created by the authors performed well in a public=
contest using a set of thousands of recordings with over 500 bird species =
from Brazil. The system was regarded as the best-performing audio only clas=
sifier, and placed second overall out of entries from 10 research groups in=
The researchers hope to drill down into more detail for their next project.
Dr Stowell says, "I'm working on techniques that can transcribe all the bir=
d 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."
The above story is based on materials provided by Queen Mary, University of=
London. Note: Materials may be edited for content and length.
Stowell D, Plumbley MD. Automatic large-scale classification of bird sounds=
is strongly improved by unsupervised feature learning. PeerJ, 2014 DOI:10.=