Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·
 

Classification of large acoustic datasets using machine learning and crowdsourcing: Application to whale calls

Publication files not online:

Author: Shamir, L. · Carol Yerby, C. · Simpson, R. · Benda-Beckmann, A.M. von · Tyack, P. · Samarra, F. · Miller, P. · Wallin, J.
Type:article
Date:2014
Source:Journal of the Acoustical Society of America, February, 2, 135, 953-962
Identifier: 488526
doi: doi:10.1121/1.4861348
Keywords: Acoustics and Audiology · Sea mammals · Whales · Whale calls · Vocal communication · Categorisation · Machine learning · Crowd sourcing · Classification · Defence Research · Defence, Safety and Security · Physics & Electronics · AS - Acoustics & Sonar · TS - Technical Sciences

Abstract

Vocal communication is a primary communication method of killer and pilot whales, and is used for transmitting a broad range of messages and information for short and long distance. The large variation in call types of these species makes it challenging to categorize them. In this study, sounds recorded by audio sensors carried by ten killer whales and eight pilot whales close to the coasts of Norway, Iceland, and the Bahamas were analyzed using computer methods and citizen scientists as part of the Whale FM project. Results show that the computer analysis automatically separated the killer whales into Icelandic and Norwegian whales, and the pilot whales were separated into Norwegian long-finned and Bahamas short-finned pilot whales, showing that at least some whales from these two locations have different acoustic repertoires that can be sensed by the computer analysis. The citizen science analysis was also able to separate the whales to locations by their sounds, but the separation was somewhat less accurate compared to the computer method. VC 2014 Acoustical Society of America