canberrabirds
|
To: | David Rees <> |
---|---|
Subject: | Sort of related - bird call ID apps |
From: | Martin Butterfield <> |
Date: | Tue, 28 Nov 2017 01:17:47 +0000 |
I suspect the key thing is the tolerances for matching the call. By that I mean does the system always have to make a match, even if only 50% confident of the ID or does it return a statement
like "Sorry no match possible"unless it is >95% confident of the match? Does it only return a single possibility or offer more than one plus probabilities (eg White throated Gerygone 55% Western Gerygone 45%).
There are many many options, its just good to see some work starting to happen since
Shazam appeared on the music scene in 2008.
Martin Butterfield
On 28 November 2017 at 11:52, David Rees
<> wrote:
|
<Prev in Thread] | Current Thread | [Next in Thread> |
---|---|---|
|
Previous by Date: | Sort of related - bird call ID apps, David Rees |
---|---|
Next by Date: | Sooty Owl, John Harris |
Previous by Thread: | Sort of related - bird call ID apps, David Rees |
Next by Thread: | FW: [canberrabirds] Pelican at Jerrabomberra wetlands, Geoffrey Dabb |
Indexes: | [Date] [Thread] [Top] [All Lists] |
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 Canberra Ornithologists Group 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 list contact David McDonald, list manager, phone (02) 6231 8904 or email . If you can not contact David McDonald e-mail Andrew Taylor at this address: andrewt@cse.unsw.EDU.AU