Spatial Bioacoustics: Soundscape Analysis with a Co-located Microphone Array

#vector #sensors #acoustics #source #separation #machine #learning

The integration of passive acoustic sensors with machine learning enables large-scale, low-cost, non-invasive monitoring of vocal animals. A remaining challenge to the successful deployment of such monitoring systems is in maintaining high classification accuracy across complex real-world soundscapes composed of overlapping calls and variable noise patterns. In this talk, we present an algorithmic pipeline for using a terrestrial co-located microphone array to (1) estimate acoustic direction-of-arrival (DoA), (2) distinguish individual sound sources in the environment, and (3) approximate their spectrograms and time-domain signals. First, we evaluate the performance of multiple DoA estimation algorithms -- including an active intensity method, white noise gain constraint beamforming, and multiple signal classification -- as well as multiple approaches for source separation -- including angular thresholding, a Gaussian mixture model, and non-negative matrix factorization. Next, we demonstrate the analysis pipeline for recordings collected at wildlife refuges during the dawn chorus in late spring, when birds are most vocally active. We significantly improve species-level performance metrics by applying source separation to the recordings prior to classification with the BirdNET network. This approach opens possibilities for additional spatiotemporal analysis of soundscapes, including the ability to visualize movement and perform directional filtering.

  Date and Time




  • Date: 09 Jun 2022
  • Time: 05:30 PM to 06:30 PM
  • All times are (UTC-04:00) Eastern Time (US & Canada)
  • Add_To_Calendar_icon Add Event to Calendar
If you are not a robot, please complete the ReCAPTCHA to display virtual attendance info.
  • 215 South Ferry Rd.
  • Narragansett, Rhode Island
  • United States 02882
  • Building: Coastal Institute (bldg. 26)
  • Click here for Map

  • Contact Event Host
  • Starts 17 May 2022 01:00 PM
  • Ends 09 June 2022 04:00 PM
  • All times are (UTC-04:00) Eastern Time (US & Canada)
  • Admission fee ?


Irina Tolkova Irina Tolkova of School of Engineering and Applied Sciences, Harvard University


Irina Tolkova is a 5th-year PhD candidate at Harvard University studying applied mathematics, with a particular interest in acoustic monitoring for wildlife conservation efforts. Her primary research focus is on utilizing sound directionality to improve automated species-level classification. In addition, she has worked on a range of projects spanning robotics, machine learning, biomedical signal processing, and quantitative ecology. Previously, Irina received bachelor’s degrees in applied math and computer science from the University of Washington, Seattle. More details on Irina’s work and hobbies can be found at


Address:United States