bioacoustics-l
[Top] [All Lists]

Improved algorithms for the automatic detection and classification of v

To: <>
Subject: Improved algorithms for the automatic detection and classification of vocalizations
From: "Ian Agranat" <>
Date: Tue, 17 Jun 2008 08:48:38 -0400
Dear fellow researchers,

We have made a number of improvements to our classification algorithms
resulting in a significant increase of detector sensitivity and accuracy.
These revised algorithms are now incorporated in version 2.0 of our Song
Scope software.  A performance analysis can be found at
http://www.wildlifeacoustics.com/songscope/v2vsv1.html comparing the
relative sensitivity and accuracy of the new and old versions when used to
detect Cerulean warbler vocalizations in 250 hours of unattended field
recordings made at several different sites of the Allegheney National
Forest.

Best regards,

Ian Agranat, President
Wildlife Acoustics, Inc.
Concord, Massachusetts, USA
www.wildlifeacoustics.com
+1 (978) 369-5225

P.s. See us at the 2008 Joint Meeting of Ichthyologists and Herpetologists
in Montreal, Booth #20

 



<Prev in Thread] Current Thread [Next in Thread>
  • Improved algorithms for the automatic detection and classification of vocalizations, Ian Agranat <=
Admin

The University of NSW School of Computer and Engineering takes no responsibility for the contents of this archive. It is purely a compilation of material sent by many people to the Bioacoustics-L mailing list. It has not been checked for accuracy nor its content verified in any way. If you wish to get material removed from the archive or have other queries about the archive e-mail Andrew Taylor at this address: andrewt@cse.unsw.EDU.AU