The Ecoacoustics Lab at QUT is researching how the collection and analysis of sound by autonomous audio recorders can scale biodiversity monitoring: www.ecosounds.org. Our research concerns the analysis of big audio data for answering ecological questions, for example to monitoring species and biodiversity. The large sound collections we capture are called soundscapes. We have developed novels ways to summarise sound using indices – statistical summaries of sound.
This research will investigate how acoustic indices can be used as features for detecting species and capturing soundscapes. Research will involve using machine learning tools such as Weka or Deep learning systems with acoustic indices. Research will involve using existing indices and potentially developing new indices.
Outcomes of the project could include new indices or ways of using indices to detect species in long duration recordings or new acoustic indices, along with research papers and reports.
Skills and experience
Students need to be interested in some of the following: machine learning, ecology, signal processing and sound.
You may be able to apply for a research scholarship in our annual scholarship round.
Contact the supervisor for more information.