Machine-learning based detection of marine mammal vocalizations in snapping-shrimp dominated ambient noise.

Journal: Marine environmental research
PMID:

Abstract

Passive acoustics is an effective method for monitoring marine mammals, facilitating both detection and population estimation. In warm tropical waters, this technique encounters challenges due to the high persistent level of ambient impulsive noise originating from the snapping shrimp present throughout this region. This study presents the development and application of a neural-network based detector for marine-mammal vocalizations in long term acoustic data recorded by us at ten locations in Singapore waters. The detector's performance is observed to be impeded by the high shrimp noise activity. To counteract this, we investigate several techniques to improve detection capabilities in shrimp noise including the use of simple nonlinear denoisers and a machine-learning based denoiser. These are shown to enhance the detection performance significantly. Finally, we discuss some of the vocalizations detected over three years of our acoustic recorder deployments using the robust detectors developed.

Authors

  • Hari Vishnu
    Acoustic Research Laboratory, 12A Kent Ridge Road, National University of Singapore, 119227, Singapore. Electronic address: harivishnu@gmail.com.
  • V R Soorya
    Acoustic Research Laboratory, 12A Kent Ridge Road, National University of Singapore, 119227, Singapore.
  • Mandar Chitre
    Acoustic Research Laboratory, 12A Kent Ridge Road, National University of Singapore, 119227, Singapore; Department of Electrical and Computer Engineering, National University of Singapore, Singapore.
  • Yuen Min Too
    Acoustic Research Laboratory, 12A Kent Ridge Road, National University of Singapore, 119227, Singapore.
  • Teong Beng Koay
    Acoustic Research Laboratory, 12A Kent Ridge Road, National University of Singapore, 119227, Singapore.
  • Abel Ho
    Acoustic Research Laboratory, 12A Kent Ridge Road, National University of Singapore, 119227, Singapore.