ANIMAL-SPOT enables animal-independent signal detection and classification using deep learning

Christian Bergler*, Simeon Q. Smeele, Stephen A. Tyndel, Alexander Barnhill, Sara T. Ortiz, Ammie K. Kalan, Rachael Xi Cheng, Signe Brinkløv, Anna N. Osiecka, Jakob Tougaard, Freja Jakobsen, Magnus Wahlberg, Elmar Nöth, Andreas Maier, Barbara C. Klump

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

79 Downloads (Pure)

Abstract

Bioacoustic research spans a wide range of biological questions and applications, relying on identification of target species or smaller acoustic units, such as distinct call types. However, manually identifying the signal of interest is time-intensive, error-prone, and becomes unfeasible with large data volumes. Therefore, machine-driven algorithms are increasingly applied to various bioacoustic signal identification challenges. Nevertheless, biologists still have major difficulties trying to transfer existing animal- and/or scenario-related machine learning approaches to their specific animal datasets and scientific questions. This study presents an animal-independent, open-source deep learning framework, along with a detailed user guide. Three signal identification tasks, commonly encountered in bioacoustics research, were investigated: (1) target signal vs. background noise detection, (2) species classification, and (3) call type categorization. ANIMAL-SPOT successfully segmented human-annotated target signals in data volumes representing 10 distinct animal species and 1 additional genus, resulting in a mean test accuracy of 97.9%, together with an average area under the ROC curve (AUC) of 95.9%, when predicting on unseen recordings. Moreover, an average segmentation accuracy and F1-score of 95.4% was achieved on the publicly available BirdVox-Full-Night data corpus. In addition, multi-class species and call type classification resulted in 96.6% and 92.7% accuracy on unseen test data, as well as 95.2% and 88.4% regarding previous animal-specific machine-based detection excerpts. Furthermore, an Unweighted Average Recall (UAR) of 89.3% outperformed the multi-species classification baseline system of the ComParE 2021 Primate Sub-Challenge. Besides animal independence, ANIMAL-SPOT does not rely on expert knowledge or special computing resources, thereby making deep-learning-based bioacoustic signal identification accessible to a broad audience.

Original languageEnglish
Article number21966
JournalScientific Reports
Volume12
Pages (from-to)21966
ISSN2045-2322
DOIs
Publication statusPublished - Dec 2022

Keywords

  • Acoustics
  • Algorithms
  • Animals
  • Area Under Curve
  • Deep Learning
  • Humans
  • Machine Learning

Fingerprint

Dive into the research topics of 'ANIMAL-SPOT enables animal-independent signal detection and classification using deep learning'. Together they form a unique fingerprint.

Cite this