At the moment, the best technology for birdsong recognition is the wetware
between our ears.
Carl Clifford
> On 15 Oct 2014, at 16:56, Paul Dodd <> wrote:
>
> Hi All,
>
> Actually, I'm not sure your response is entirely accurate, Allan.
>
> There is a project by the University of Wisconsin called "WeBird" that is
> designed to do exactly this. You can capture the sound of birds calling
> using the microphone on your iPhone, and the software will tell you the
> species of bird. Or so the blurb goes...
> http://grow.cals.wisc.edu/environment/smart-birding I am not sure how close
> WeBird is to commercialisation - it was slated for release in 2013, but I
> haven't seen or heard anything about whether this date was met. There is a
> free download of an iPhone app, but it hasn't been updated since 2011, so
> you'd have to wonder if it has been abandoned.
>
> I suspect, though, that in many respects, Allan's response is accurate.
>
> The way that the music recognition app Shazam and similar work on the iPhone
> and similar devices is that they take a sample of the music playing (even
> humming and whistling) and compress this into a small amount of data that
> can then be compared with a vast library of captured and recorded tunes.
> Once a subset of the vast library has been identified, larger data samples
> are compared until a match is found (or not).
>
> What makes all of this work is two things fundamentally: a HUGE library of
> sampled songs and a HUGE array of servers with incredibly high performance.
> What is likely missing in the birding world is both of these - there is no
> huge library of sampled bird song and I suspect that the University of
> Wisconsin and any other birder-related organisation is unlikely to have the
> funds to afford a huge array of fast servers needed for the data processing.
>
> Interestingly, the variety of calls wouldn't matter greatly as the software
> uses an averaging approach - tightening the parameters to do with the
> averaging would simply mean that a closer match was required, or relaxing
> the parameters would allow for more matches (and more likelihood of
> erroneous matches).
>
> I think that it is likely that we will have apps that can do this in the
> reasonably near future provided that a large enough sample set of calls
> becomes available - the servers and hardware will be cheap enough in time as
> computing power doubles approximately every 18 months - and prices probably
> halve in the same time period!
>
> Paul Dodd
> Docklands, Victoria
>
>
>
> -----Original Message-----
> From: Birding-Aus On Behalf Of
> Allan Richardson
> Sent: Wednesday, 15 October 2014 3:27 PM
> To: Michael Hunter
> Cc:
> Subject: Re: [Birding-Aus] song recognition apps
>
> Hi Michael,
>
> The short answer is no.
>
> What you'd like and what technology can provide in this case are miles
> apart.
>
> There is a recording device available that records bird calls and has
> software for reading the calls. However, you have to record, identify and
> then build a library of calls for the software to identify.
>
> However the technology is not reliable for a number of reasons, and the
> number of call variations you would require to cover Australia's avi-fauna
> is beyond computation.
>
> The software has difficulty in identifying the calls, due to variation in
> intensity, pitch, shape and other noises masking the calls, so finding a
> good set of "standard calls" that the software could recognise would be
> difficult.
>
> Not only that, in any given area you may have as many as 200 or more birds
> that could be possible, and this multiplied by the number of call variations
> and loudness would be very difficult for software to work out.
>
> Hopefully a new way of deciphering calls will become available, but at the
> moment it doesn't exist.
>
> The ability of the human ear and brain to identify the calls of birds is
> very difficult to emulate in the electronic world, due to the often subtle
> variation between species and within species vocalisations.
>
> I wish the answer could be of more help - the best thing to do is get out,
> hear a bird call and then track it down and identify it.
>
> Yes it's slow and time consuming, and often frustrating, but these problems
> are what makes bird identification so rewarding in the long-run.
>
> Happy birding,
>
> Allan Richardson
>
>
> On 15 Oct 2014, at 10:28 am, Michael Hunter <>
> wrote:
>
>> Hi All.
>>
>> Are there any Australian Bird apps which identify bird calls or
> songs in the field. ie which "hear" the vocalisations and can identify the
> species which is calling?
>>
>> Cheers Michael
>> <HR>
>> <BR> Birding-Aus mailing list
>> <BR>
>> <BR> To change settings or unsubscribe visit:
>> <BR> http://birding-aus.org/mailman/listinfo/birding-aus_birding-aus.org
>> </HR>
>
>
> <HR>
> <BR> Birding-Aus mailing list
> <BR>
> <BR> To change settings or unsubscribe visit:
> <BR> http://birding-aus.org/mailman/listinfo/birding-aus_birding-aus.org
> </HR>
>
>
> <HR>
> <BR> Birding-Aus mailing list
> <BR>
> <BR> To change settings or unsubscribe visit:
> <BR> http://birding-aus.org/mailman/listinfo/birding-aus_birding-aus.org
> </HR>
<HR>
<BR> Birding-Aus mailing list
<BR>
<BR> To change settings or unsubscribe visit:
<BR> http://birding-aus.org/mailman/listinfo/birding-aus_birding-aus.org
</HR>
|
