Validation prediction: a flexible protocol to increase efficiency of automated acoustic processing for wildlife research. Issue 7 (26th May 2020)

• Record Type: Journal Article
• Authors: Knight, Elly C.; Sòlymos, Péter; Scott, Chris; Bayne, Erin M.
• Is Part Of: Ecological applications. Volume 30:Issue 7(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-05-26
• Subjects: autonomous recording unit (ARU) -- bioacoustic -- bird -- machine learning -- passive acoustic monitoring -- recognizer -- signal processing; Ecology -- Periodicals; Environmental protection -- Periodicals; Biology, Economic -- Periodicals; 577.05
• DOI: 10.1002/eap.2140
• Languages: English
• ISSNs: 1051-0761

Abstract

Abstract: Automated recognition is increasingly used to extract species detections from audio recordings; however, the time required to manually review each detection can be prohibitive. We developed a flexible protocol called "validation prediction" that uses machine learning to predict whether recognizer detections are true or false positives and can be applied to any recognizer type, ecological application, or analytical approach. Validation prediction uses a predictable relationship between recognizer score and the energy of an acoustic signal but can also incorporate any other ecological or spectral predictors (e.g., time of day, dominant frequency) that will help separate true from false‐positive recognizer detections. First, we documented the relationship between recognizer score and the energy of an acoustic signal for two different recognizer algorithm types (hidden Markov models and convolutional neural networks). Next, we demonstrated our protocol using a case study of two species, the Common Nighthawk ( Chordeiles minor ) and Ovenbird ( Seiurus aurocapilla ). We reduced the number of detections that required validation by 75.7% and 42.9%, respectively, while retaining at least 98% of the true‐positive detections. Validation prediction substantially improves the efficiency of using automated recognition on acoustic data sets. Our method can be of use to wildlife monitoring and research programs and will facilitate using automated recognition to mine bioacoustic data sets.