Detecting bird sound in unknown acoustic background using crowdsourced training data
This addresses biodiversity monitoring for ecologists and conservationists by enabling scalable, automated detection of bird species in noisy recordings, though it is incremental as it adapts existing novelty detection concepts to this domain.
The paper tackles the problem of detecting bird vocalizations in diverse and complex acoustic backgrounds by building generative models of bird sounds and using novelty detection, achieving detection results across various acoustic environments and signal-to-noise ratios.
Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crowdsourcing using recording and species recognition on mobile devices. The ability, however, to reliably identify vocalising animal species is limited by the fact that acoustic signatures of interest in such recordings are typically embedded in a diverse and complex acoustic background. To avoid the problems associated with modelling such backgrounds, we build generative models of bird sounds and use the concept of novelty detection to screen recordings to detect sections of data which are likely bird vocalisations. We present detection results against various acoustic environments and different signal-to-noise ratios. We discuss the issues related to selecting the cost function and setting detection thresholds in such algorithms. Our methods are designed to be scalable and automatically applicable to arbitrary selections of species depending on the specific geographic region and time period of deployment.