escience2019 has ended
Back To Schedule
Wednesday, September 25 • 5:45pm - 6:15pm
Recognition of Frog Chorusing with Acoustic Indices and Machine Learning

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Hongxiao Gan (Queensland University of Technology), Jinglan Zhang (Queensland University of Technology), Michael Towsey (Queensland University of Technology), Anthony Truskinger (Queensland University of Technology), Debra Stark (The University of Queensland), Berndt van Rensburg (The University of Queensland), Yuefeng Li (Queensland University of Technology), and Paul Roe (Queensland University of Technology)

This research explores the recognition of choruses of two co-existing sibling frog species in long-duration field recordings using false-colour spectrograms and acoustic indices. Acid frogs are a group of endemic frogs that are particularly sensitive to habitat change and competition from other species. Wallum Sedgefrogs (Litoria olongburensis) are the most threatened acid frog species facing habitat loss and degradation across much of their distribution, in addition to further pressures associated with anecdotally-recognised competition from their sibling species, the Eastern Sedgefrogs (Litoria fallax). Monitoring the calling behaviours of these two species is essential for informing L. olongburensis management and protection, and for obtaining ecological information about the process and implications of their competition. Since their habitats can easily be disturbed by human activity and their body size is very small, passive acoustic monitoring is a good method to monitor their activities. However, after accumulating months of field recordings, it is a time-consuming and labour-intensive task to listen through recordings to identify the two species. Therefore, there is a high demand for automated acoustic pattern and species recognition tools to efficiently navigate months of recordings and identify target species. Our research provides more insight on how to choose acoustic features to efficiently recognise species from fieldcollected recordings at a larger scale. The experimental results show that these techniques are useful to identify choruses of the two competitive frog species with an accuracy of 76.7% on identifying four acoustic patterns (whether the two species occurred).


Hongxiao Gan

Queensland University of Technology

Wednesday September 25, 2019 5:45pm - 6:15pm PDT
Macaw Room