Assemblage of Focal Species Recognizers - AFSR: A technique for decreasing false positive rates of acoustic automatic identification in a multiple species context
Preprint
- 11 February 2019
- preprint
- Published by Cold Spring Harbor Laboratory in bioRxiv
- p. 546812
Abstract
Passive acoustic monitoring (PAM) coupled with automated species identification is a promising tool for species monitoring and conservation worldwide. However, high false positive rates are still an important limitation and a crucial factor for acceptance of these techniques in wildlife surveys. Here we present the Assemblage of Focal Species Recognizers - AFSR, a novel approach for decreasing false positives and increasing models’ precision in multispecies contexts. AFSR focusses on decreasing false positives by excluding unreliable sound file segments that are prone to misidentification. We used MatlabHTK, a hidden Markov models interface for bioacoustics analyses, for illustrating AFSR technique by comparing two approaches, 1) a multispecies recognizer where all species are identified simultaneously, and 2) an assemblage of focal species recognizers (AFSR), where several recognizers that each prioritise a single focal species are then summarised into a single output, according to a set of rules designed to exclude unreliable segments. Both approaches (the multispecies recognizer and AFSR) used the same sound files training dataset, but different processing workflow. We applied these recognisers to PAM recordings from a remote island colony with five seabird species and compared their outputs with manual species identifications. False positive rates and precision improved for all the five species when using AFSR, achieving remarkable 0% false positives and 100% precision for three of five seabird species, and < 6% false positive rates, and >90% precision for the other two species. AFSR’ output was also used to generate daily calling activity patterns for each species. Instead of attempting to withdraw useful information from every fragment in a sound recording, AFSR prioritises more trustworthy information from sections with better quality data. AFSR can be applied to automated species identification from multispecies PAM recordings worldwide.Keywords
All Related Versions
- Published version: PLOS ONE, 14 (12), e0212727.
This publication has 21 references indexed in Scilit:
- On-Bird Sound Recordings: Automatic Acoustic Recognition of Activities and ContextsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Soundscape analysis and acoustic monitoring document impacts of natural gas exploration on biodiversity in a tropical forestEcological Indicators, 2017
- Multiple-Instance Multiple-Label Learning for the Classification of Frog Calls with Acoustic Event Detection2016
- Decoding Group Vocalizations: The Acoustic Energy Distribution of Chorus Howls Is Useful to Determine Wolf ReproductionPLOS ONE, 2016
- A novel citizen science approach for large-scale standardised monitoring of bat activity and distribution, evaluated in eastern EnglandBiological Conservation, 2015
- Integration over song classification replicates: Song variant analysis in the hihiThe Journal of the Acoustical Society of America, 2015
- An evaluation of manual and automated methods for detecting sounds of maned wolves (Chrysocyon brachyurusIlliger 1815)Bioacoustics, 2015
- A Hidden Markov Model-Based Acoustic Cicada Detector for Crowdsourced Smartphone Biodiversity MonitoringJournal of Artificial Intelligence Research, 2014
- Acoustic monitoring of nocturnally migrating birds accurately assesses the timing and magnitude of migration through the Great LakesOrnithological Applications, 2014
- Semi-automatic long-term acoustic surveying: A case study with batsEcological Informatics, 2014