A variety of native birds can be likely heard by anyone who wanders into the New Zealand bush. However, identifying which bird is which, especially if they imitate each other, will not be easy.
A Professor from Victoria University of Wellington’s School of Mathematics and Statistics, together with his research team, had created software that can analyse sound recordings from the New Zealand bush and deduce the abundance of various types of birds.
According to a recent press release, AviaNZ allows them to monitor the health of bird populations without affecting their behaviours.
What can the software do?
Additionally, the technology could also monitor pests and predators by changing the types of recorders being used.
It could also be an excellent way to gauge the predator stress on a particular area.
The software can be trained to recognise any sound. As long as the predators are talking to each other and the microphone is close enough, it will be able to detect them.
The team have successfully trained the software to detect two types of native bats, which are inaudible to humans.
The software analyses spectrogram recordings, or the visual representations of sound waves, of bush sounds.
It then learns the sound waves patterns that represent each bird call and can count how many of those bird calls occur.
It is not as good as an expert human, who is concentrating hard at discerning the different calls. However, it is quite difficult for a human to maintain concentration to any 8-hour recording, while most of it is nothing, with no calls at all.
The software, on the other hand, does not care. Plus, it is very fast. A 15-minute recording takes it about a minute to process.
Current challenges
The team is currently working on being able to identify the direction and distance of the calls from the recorders as well as naming the individual birds.
They cannot differentiate yet if the 50 calls are from 5 birds making 10 calls each or 50 birds each calling once, but they are moving toward that.
The ultimate aim is to turn this into estimates of the abundance of different species.
Funding from the Science for Technological Innovation’s National Science Challenge was used to develop a different recorder that uses multiple microphones to mathematically auto-correlate the direction the sounds are coming from and their distance from the microphones.
The distance and direction aspects of this project are potentially very useful.
Once the location of the calls have been worked out, the number of birds that are doing the talking can be established.
The team have built a prototype recorder that can successfully estimate the direction of calls but have found estimating the distance from the recorder to be more difficult.
They will continue to work on this aspect of the recorder to improve their software and help contribute to conservation efforts in New Zealand.