A concern for applications of machine learning techniques to bioacoustics is whether or not classifiers learn the categories for which they were trained. Unfortunately, information such as characteristics of specific recording equipment or noise environments can also be learned. This question is examined in the context of identifying delphinid species by their echolocation clicks. To reduce the ambiguity between species classification performance and other confounding factors, species whose clicks can be readily distinguished were used in this study: Pacific white-sided and Risso's dolphins. A subset of data from autonomous acoustic recorders located at seven sites in the Southern California Bight collected between 2006 and 2012 was selected. Cepstral-based features were extracted for each echolocation click and Gaussian mixture models were used to classify groups of 100 clicks. One hundred Monte-Carlo three-fold experiments were conducted to examine classification performance where fold composition was determined by acoustic encounter, recorder characteristics, or recording site. The error rate increased from 6.1% when grouped by acoustic encounter to 18.1%, 46.2%, and 33.2% for grouping by equipment, equipment category, and site, respectively. A noise compensation technique reduced error for these grouping schemes to 2.7%, 4.4%, 6.7%, and 11.4%, respectively, a reduction in error rate of 56%–86%.
Skip Nav Destination
Article navigation
January 2015
January 01 2015
Compensating for the effects of site and equipment variation on delphinid species identification from their echolocation clicks
Marie A. Roch;
Marie A. Roch
a)
Department of Computer Science,
San Diego State University
, 5500 Campanile Drive, San Diego, California 92182-7720
Search for other works by this author on:
Johanna Stinner-Sloan;
Johanna Stinner-Sloan
Department of Computer Science,
San Diego State University
, 5500 Campanile Drive, San Diego, California 92182-7720
Search for other works by this author on:
Simone Baumann-Pickering;
Simone Baumann-Pickering
Scripps Institution of Oceanography,
University of California
, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0205
Search for other works by this author on:
Sean M. Wiggins
Sean M. Wiggins
Scripps Institution of Oceanography,
University of California
, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0205
Search for other works by this author on:
a)
Author to whom correspondence should be addressed. Electronic mail: marie.roch@sdsu.edu
J. Acoust. Soc. Am. 137, 22–29 (2015)
Article history
Received:
June 19 2014
Accepted:
November 12 2014
Citation
Marie A. Roch, Johanna Stinner-Sloan, Simone Baumann-Pickering, Sean M. Wiggins; Compensating for the effects of site and equipment variation on delphinid species identification from their echolocation clicks. J. Acoust. Soc. Am. 1 January 2015; 137 (1): 22–29. https://doi.org/10.1121/1.4904507
Download citation file:
Sign in
Don't already have an account? Register
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Sign in via your Institution
Sign in via your InstitutionPay-Per-View Access
$40.00