Tom Denton introduces A2O Search, a project I’ve been working on throughout the year:
Today, we’re expanding this collaboration with the launch of A2O Search. This new sound search engine, built with Google AI, allows researchers and scientists to search through millions of hours of Australian wildlife audio collected by the Australian Acoustics Observatory (A2O).
Traditionally, researchers analysed wildlife audio by manually listening through hours of audio clips to identify an animal sound. This painstaking and laborious process posed barriers for research and has hindered land management decisions. Even with the introduction of machine learning tools for classification, collecting training data is an enormous undertaking and limits the number and kinds of questions that scientists can answer.
I’ve worked on the front-end, which allows researchers to upload an audio recording to search for similar recordings in A2O’s database. The recording is visualised in a spectrogram and researchers can clip the recording to a five-second junk to narrow down the audio input. The results can be viewed and filtered by location, date or time of day.
The project also received coverage in Australian news.
“What we have built here is a search tool to liberate the data collected in the field. Instead of trying to manually sift through what amounts to hundreds of years of data that we could not live long enough to go through, AI does it for us,”
Researchers hope the audio search engine will yield important insights into where some animals go after bushfires and other natural disasters, and to better understand the impact of climate change and the spread of invasive species.