weka.jpg

AviaNZ birdsong analysis software

AviaNZ version 1.3 is released with some improvemets and bug fixes! The program is easy to use and equipped with the essentials for spectrogram reading, analysis, manual annotation, and also few other stimulating options to the next stage of the development: automated analysis of your field recordings. You can download the software along with the user manual following the links below. We thank to those of you who shared your experence while using the program with us enabling to improve it. We welcome your feedback and it is very important to us as we continue developing AviaNZ.

 AviaNZ  

Download User Manual

Last update: 24 Oct2018

 
 
Windows  Download AviaNZ v1.3
Mac & Linux Download code
  Instructions

Marsden Fund for AviaNZ

Stephen Marsland and Isabel Castro received Marsden Fund in this latest round to work on their project  AviaNZ: Making Sure New Zealand Birds Are Heard.

Stephen Marsland and Isabel Castro with Blandy the kiwi

Read More

Sponsor a kiwi

To track and study our kiwi, they each need individual radio-transmitters and we need radio-telemetry equipment, batteries, and cameras to be able to follow them. In total, we spend $470 per kiwi each year and we would like to ask you to sponsor this cost for one or more of our birds.

Sponsor a kiwi

 Learn More

Stephen Marsland and Isabel Castro received Marsden Fund in this latest round to work on their project AviaNZ: Making Sure New Zealand Birds Are Heard.

Stephen Marsland and Isabel Castro with Blandy the kiwi

New Zealand has amazing birdlife: nocturnal parrots, birds that can't fly, and birds that turn up after 50 years of being thought extinct. Unfortunately, many native species require wildlife management programmes, and they are hard to monitor: they are often well-camouflaged or nocturnal. How can you discern what works in wildlife management if you don't know how many animals there are and how the number changes? Most birds make sound, and so there is a real need for a system that can detect, recognise, analyse, and infer bird populations using automated sound recorders. However, data from these recorders is noisy and extremely variable in factors such as volume. In this project we will work to reliably detect and recognise birdsong from these recordings, and estimate the abundance of birds from the number of calls, by developing mathematical and computational tools to analyse sound, and combining them with ecological experiments to understand how calls relate to population estimates. This inter-disciplinary project will combine fundamental and practical work in theoretical and experimental science to develop sound solutions in both areas. Our work will be made publicly available through our AviaNZ software platform, which is already used by conservation groups across the country.

 

Featured Research

Automated birdsong recognition in complex acoustic environments: a review
Priyadarshani, N. , Marsland, S. and Castro, I. (2018), Automated birdsong recognition in complex acoustic environments: a review. J Avian Biol, 49: jav-01447. doi:10.1111/jav.01447 
 
The impact of environmental factors in birdsong acquisition using automated recorders
Priyadarshani N, Castro I, Marsland S. (2018), The impact of environmental factors in birdsong acquisition using automated recorders. Ecol Evol. 2018;8:5016–5033. doi.org/10.1002/ece3.3889
 
Birdsong Denoising Using Wavelets
Priyadarshani N, Marsland S, Castro I, Punchihewa A (2016) Birdsong Denoising Using Wavelets. PLoS ONE 11(1): e0146790. doi.org/10.1371/journal.pone.0146790
Related image  Denoised examples and source code
 
Experimental test of birdcall detection by autonomous recorder units and by human observers using broadcast
Isabel Castro, Alberto De Rosa, Nirosha Priyashardani, Leanne Bradbury and Stephen Marsland (2018), Experimental test of birdcall detection by autonomous recorder units and by human observers using broadcast. Ecology and Evolution [accepted for publication]