An automated, real time classification system for biological and anthropogenic sounds from fixed ocean observatories

Abstract

The automated, real time classification of acoustic events in the marine environment is an important tool to study anthropogenic sound pollution, marine mammals and for mitigating human activities that are potentially harmful. We present a real time classification system targeted at many important groups of acoustic events (clicks, buzzes, calls, whistles from several cetacean species, tonal and impulsive shipping noise and explosions). The achieved classification performance indicates that the system will be useful to pre-process the very large data volume that can be gathered during long term acoustic monitoring campaigns or to detect the presence of cetaceans in real time for mitigation.