aMOBY — Acoustic Monitoring of Biodiversity

Welcome to the project web site of aMOBY, an applied research project at the Austrian Institute for Artificial Intelligence (OFAI), together with Monika Dörfler (NuHAG, University of Vienna), sponsored by the Vienna Science and Technology Fund (WWTF, project NXT17-004).

Our goal is to demonstrate if and how well modern artificial neural networks can detect and distinguish animal species by their calls. This is especially interesting in the context of biodiversity monitoring: It may allow to perform continuous monitoring of habitats to quantify the status and changes in biological diversity, supplementing observations by sight.
We specifically focus our experiments on birds and whales, but use methods that are general enough to adapt to other animal recordings, as long as enough annotated examples are available. Please contact us if you face any related problem that we might help you with!

Demonstrations

two flying parrots

Bird Detection

As a first step, we investigated detecting whether a given audio recording contained any bird calls, as opposed to other sound or even human bird imitations. see more

a microphone

Bird Detection Demo

Try for yourself whether you can fool our bird detector by recording your voice or uploading audio files from your computer. see more

closeup of a whale

Whale Detection

To go for a different domain, we will explore the detection of blue whales from underwater recordings. see more

Get In Touch

This project merely serves to demonstrate what is possible with current technology. If you work on a related problem — be it in academia or industry — we are highly interested in hearing from you! Please send us an email or give us a call and we will figure out a way to collaborate.