At 09:29 AM 9/8/2002, Bernie Krause wrote:
>Does anyone know of a good match-to-sample software that is
>available? Looking for something that could be conformed to identify
>bird vox w/in the context of an entire biophony.
I think this is the piece of software we all want - recordists as well as
biologists who want to census an area, such as a marsh or a rain forest. In=
all the discussions and correspondence I have received, nobody has yet
developed anything really workable. A few are working on it.
I think that this group could do a lot in initiating such software -
setting the parameters, discussing the algorithms necessary, etc. The
primary problem, of course, is that the number of variables is astounding.=
Even a very simple, well-known biophony is really difficult.
I have tried to do even a simple text key to sounds in my local marsh, and=
gave up after the project became too massive to be useful! I think, though,=
that this is where one would start - on a "key" to sounds: "Is it a song or=
a call?" If it is a song go to "B", if it is a call, go to "C"... already
ungainly. If we could get it done in text, that could form the basis for
the software algorithm that would be used.
Doug
Doug Von Gausig
Clarkdale, Arizona, USA
Moderator
Nature Recordists e-mail group
http://groups.yahoo.com/group/naturerecordists
[Non-text portions of this message have been removed]
________________________________________________________________________
________________________________________________________________________
|