This paper presents an automatic classification method dedicated to mysticete calls. This method relies on sparse representations which assume that mysticete calls lie in a linear subspace described by a dictionary-based representation. The classifier accounts for noise by refusing to assign the observed signal to a given class if it is not included into the linear subspace spanned by the dictionaries of mysticete calls. Rejection of noise is achieved without feature learning. In addition, the proposed method is modular in that, call classes can be appended to or removed from the classifier without requiring retraining. The classifier is easy to design since it relies on a few parameters. Experiments on five types of mysticete calls are presented. It includes Antarctic blue whale Z-calls, two types of “Madagascar” pygmy blue whale calls, fin whale 20 Hz calls and North-Pacific blue whale D-calls. On this dataset, containing 2185 calls and 15 000 noise samples, an average recall of 96.4% is obtained and 93.3% of the noise data (persistent and transient) are correctly rejected by the classifier.
Skip Nav Destination
Article navigation
September 2018
September 25 2018
Sparse representation-based classification of mysticete calls Available to Purchase
Thomas Guilment;
Thomas Guilment
a)
IMT Atlantique, Lab-STICC, Bretagne Loire University
, Technopole Brest-Iroise CS83818, Brest 29238, France
Search for other works by this author on:
Francois-Xavier Socheleau;
Francois-Xavier Socheleau
IMT Atlantique, Lab-STICC, Bretagne Loire University
, Technopole Brest-Iroise CS83818, Brest 29238, France
Search for other works by this author on:
Dominique Pastor;
Dominique Pastor
IMT Atlantique, Lab-STICC, Bretagne Loire University
, Technopole Brest-Iroise CS83818, Brest 29238, France
Search for other works by this author on:
Simon Vallez
Simon Vallez
Sercel
, 12 Rue de la Villeneuve, 29200 Brest, France
Search for other works by this author on:
Thomas Guilment
a)
IMT Atlantique, Lab-STICC, Bretagne Loire University
, Technopole Brest-Iroise CS83818, Brest 29238, France
Francois-Xavier Socheleau
IMT Atlantique, Lab-STICC, Bretagne Loire University
, Technopole Brest-Iroise CS83818, Brest 29238, France
Dominique Pastor
IMT Atlantique, Lab-STICC, Bretagne Loire University
, Technopole Brest-Iroise CS83818, Brest 29238, France
Simon Vallez
Sercel
, 12 Rue de la Villeneuve, 29200 Brest, France
a)
Electronic mail: [email protected]
J. Acoust. Soc. Am. 144, 1550–1563 (2018)
Article history
Received:
April 06 2018
Accepted:
August 28 2018
Citation
Thomas Guilment, Francois-Xavier Socheleau, Dominique Pastor, Simon Vallez; Sparse representation-based classification of mysticete calls. J. Acoust. Soc. Am. 1 September 2018; 144 (3): 1550–1563. https://doi.org/10.1121/1.5055209
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
Climatic and economic fluctuations revealed by decadal ocean soundscapes
Vanessa M. ZoBell, Natalie Posdaljian, et al.
Variation in global and intonational pitch settings among black and white speakers of Southern American English
Aini Li, Ruaridh Purse, et al.
The contribution of speech rate, rhythm, and intonation to perceived non-nativeness in a speaker's native language
Ulrich Reubold, Robert Mayr, et al.
Related Content
Classification of mysticete sounds using machine learning techniques
J. Acoust. Soc. Am. (November 2013)
Methods for automatic detection of mysticete calls
J. Acoust. Soc. Am. (November 1994)
A Comparison of Mysticete and Odontocete Cetacean Acoustic Signals and Their Behavioral Consequences
J. Acoust. Soc. Am. (January 1973)
Mysticete whale sounds and human speech
J. Acoust. Soc. Am. (August 2005)
Anatomy of infrasonic communication in baleen whales: Divergent mechanisms of sound generation in mysticetes and odontocetes
J. Acoust. Soc. Am. (May 2004)