Abstract
Abstract The avian dawn chorus presents a challenging opportunity to test autonomous recording units (ARUs) and associated recogniser software in the types of complex acoustic environments frequently encountered in the natural world. To date, extracting information from acoustic surveys using readily-available signal recognition tools (‘recognisers’) for use in biodiversity surveys has met with limited success. Combining signal detection methods used by different recognisers could improve performance, but this approach remains untested. Here, we evaluate the ability of four commonly used and commercially- or freely-available individual recognisers to detect species, focusing on five woodland birds with widely-differing song-types. We combined the likelihood scores (of a vocalisation originating from a target species) assigned to detections made by the four recognisers to devise an ensemble approach to detecting and classifying birdsong. We then assessed the relative performance of individual recognisers and that of the ensemble models. The ensemble models out-performed the individual recognisers across all five song-types, whilst also minimising false positive error rates for all species tested. Moreover, during acoustically complex dawn choruses, with many species singing in parallel, our ensemble approach resulted in detection of 74% of singing events, on average, across the five song-types, compared to 59% when averaged across the recognisers in isolation; a marked improvement. We suggest that this ensemble approach, used with suitably trained individual recognisers, has the potential to finally open up the use of ARUs as a means of automatically detecting the occurrence of target species and identifying patterns in singing activity over time in challenging acoustic environments.
Highlights
Autonomous recording units (ARUs) are increasingly used to gather ecological data for a diverse array of sound-producing animal taxa, including insects, anurans, cetaceans, bats, primates and birds (Sugai et al, 2019)
The sensitivity of the ensemble model at the optimal roc01 cutpoint value for each study species averaged 74% amongst the species, whilst sensitivity averaged across all component recognisers and study species at their respective optimal roc01 cutpoint values was 59%
If automated acoustic recognisers are to be more widely adopted in ecological studies, there is a need for improved recogniser performance in detecting and classifying vocalisations within noisy acoustic surveys
Summary
Autonomous recording units (ARUs) are increasingly used to gather ecological data for a diverse array of sound-producing animal taxa, including insects, anurans, cetaceans, bats, primates and birds (Sugai et al, 2019). In common with other automated data collection methods in ecology (e.g. camera-traps; Norouzzadeh et al, 2018), the rate-limiting step in biodiversity studies using such data, is that of extracting information from the considerable datasets amassed. This can involve manually browsing many hours of sound recordings on spectrograms, which is a laborious task (SebastiánGonzález et al, 2015), potentially requiring costly teams of sound analysts Despite progress in recent years, the performance of signal recognition systems has failed to keep pace with advances in acoustic data collection and storage (Wimmer et al, 2013)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
