1887
banner image
No data available.
Please log in to see this content.
You have no subscription access to this content.
No metrics data to plot.
The attempt to load metrics for this article has failed.
The attempt to plot a graph for these metrics has failed.
Automated extraction and classification of time-frequency contours in humpback vocalizations
Rent:
Rent this article for
USD
10.1121/1.4770251
/content/asa/journal/jasa/133/1/10.1121/1.4770251
http://aip.metastore.ingenta.com/content/asa/journal/jasa/133/1/10.1121/1.4770251

Figures

Image of FIG. 1.
FIG. 1.

(Color online) Spectrogram enhancement with a two-dimensional Gaussian filter. (a) A spectrogram showing six humpback whale calls recorded in the Auau chanel, Hawaii, during February to April of 2002. These units are labeled A-F from left to right. White Gaussian noise was added to the data to illustrate the effect of image enhancement. (b) Enhanced spectrogram using a 7 × 7 Gaussian filtering mask, with standard deviation σ = 0.9.

Image of FIG. 2.
FIG. 2.

Edge points extracted from the spectrogram shown in Fig. 1 . The edge points are connected to make contour lines. Note the all the units have been correctly detected at the fundamental frequency.

Image of FIG. 3.
FIG. 3.

(Color online) Six unit types selected from the Auau data and the FFS data, for the controlled test of unit clustering algorithm. Each class consists of five units.

Image of FIG. 4.
FIG. 4.

Examples of the U-d type units which illustrates the variation of time- frequency contour of the same unit type. These units were repeated by the same singer for about 2 min.

Image of FIG. 5.
FIG. 5.

(Color online) Twelve unit types extracted from the Auau 2002 data. The spectrogram displays the cluster-center unit of each unit type.

Tables

Generic image for table
TABLE I.

Probability of false alarm (PFA ) versus probability of missed detection (PMD ) using the contour extraction algorithm for humpback unit detection. Case 1 is with snapping shrimp noise, and Case 2 is with boat noise.

Generic image for table
TABLE II.

Implementation of the unit clustering algorithm. The algorithm returns the class arrays { k }, k = 1, 2,…, K, with K being the number of classes.

Generic image for table
TABLE III.

Composition of the six unit types for the controlled test. The frequency range f min and f max are specified for the time-frequency contour measured at the fundamental frequency.

Loading

Article metrics loading...

/content/asa/journal/jasa/133/1/10.1121/1.4770251
2013-01-03
2014-04-23
Loading

Full text loading...

This is a required field
Please enter a valid email address
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Automated extraction and classification of time-frequency contours in humpback vocalizations
http://aip.metastore.ingenta.com/content/asa/journal/jasa/133/1/10.1121/1.4770251
10.1121/1.4770251
SEARCH_EXPAND_ITEM