Poll: Seeking Your Interest in Sound+Vision AI Workshop: Demo on Detecting Sneezing or Dog barking?

Maybe the system could also try and detect a match against a database of known interference signals such as a car, lawn mower, children playing and positive matches nulled from the input signal. Such data could be collected in a highly urbanised environment to exclude birds singing or perhaps at night (maybe not the lawnmower ! ). Unfortunately my short overview would require a lot of processing power and coding to realise.

You could perhaps filter on bandwidth to negate rumblings of tyres on asphalt etc or notch out some really specific interference like a neighbour's hedge trimmer.

beacon_dave  While this makes good sense, I can't help but chuckle thinking that my local birds have an accent.  Tweet, don't ya know, eh? Oh. tweet, you betcha.  (Wisconsin, USA)

One issue related to this may be with the birds that have started to mimic urban human noise pollution. e.g. you can now get birds mimicking car alarms. So the training data set may have to be tweaked to be able to accommodate this to prevent ending up with photos of 'the lesser spotted Ferrari'. Although in this case, just got to get the second stage vision classification process to successfully detect between a bird and a car in order to reduce the error.

Another issue may be the regional localisation of birds. Existing data sets are probably pretty good for the region the primary research was conducted in but perhaps not so good globally.

Doing bird types would be interesting as well.

DAB

From the sample I have had with dogs I have owned and observed, each type as a unique sound, so discrimination of type should be possible.

DAB

Spinden,

Birds should be possible although we get a lot of background noise from planes, automobiles, wind in the trees, shouting people and so on.  Especially as most audio amplifiers use automatic gain controls which just amplifies the background 'hiss/noise' when there is no target noise available.

Dubbie

DAB,

I wonder if dogs have unique 'voices' like people do so you could identify a specific dog from within a whole cacophony of dogs. Experimental trials could be a problem - with the neighbours.

Dubbie

Dave,

I hadn't thought of using a dog to detect a cat. I wonder if it would work? Still, as you say, the drawback is that you have to have a dog which poo and dig in the garden. So then I would need something to detect digging in the garden.

Dubbie

What about any animal? I think it would be great to identify types of birds too.

What about detecting dog barking, then determining type of dog?

DAB