Recognizing transient low-frequency whale sounds by spectrogram correlation.

A method is described for the automatic recognition of transient animal sounds. Automatic recognition can be used in wild animal research, including studies of behavior, population, and impact of anthropogenic noise. The method described here, spectrogram correlation, is well-suited to recognition of animal sounds consisting of tones and frequency sweeps. For a sound type of interest, a two-dimensional synthetic kernel is constructed and cross-correlated with a spectrogram of a recording, producing a recognition function--the likelihood at each point in time that the sound type was present. A threshold is applied to this function to obtain discrete detection events, instants at which the sound type of interest was likely to be present. An extension of this method handles the temporal variation commonly present in animal sounds. Spectrogram correlation was compared to three other methods that have been used for automatic call recognition: matched filters, neural networks, and hidden Markov models. The test data set consisted of bowhead whale (Balaena mysticetus) end notes from songs recorded in Alaska in 1986 and 1988. The method had a success rate of about 97.5% on this problem, and the comparison indicated that it could be especially useful for detecting a call type when relatively few (5-200) instances of the call type are known.

[1]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[2]  I. Whitfield,et al.  RESPONSES OF AUDITORY CORTICAL NEURONS TO STIMULI OF CHANGING FREQUENCY. , 1965, Journal of neurophysiology.

[3]  R. Graber,et al.  Nocturnal Migration in Illinois: Different Points of View , 1968 .

[4]  P. O. Thompson,et al.  Underwater Sounds from the Blue Whale, Balaenoptera musculus , 1971 .

[5]  R. Payne,et al.  Songs of Humpback Whales , 1971, Science.

[6]  R. Kay,et al.  On the existence in human auditory pathways of channels selectively tuned to the modulation present in frequency‐modulated tones , 1972, The Journal of physiology.

[7]  D. Hubel,et al.  Ferrier lecture - Functional architecture of macaque monkey visual cortex , 1977, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[8]  A R Møller.  Coding of time-varying sounds in the cochlear nucleus. , 1978, Audiology : official organ of the International Society of Audiology.

[9]  R. Altes.  Detection, estimation, and classification with spectrograms , 1980 .

[10]  Christopher W. Clark,et al.  The acoustic repertoire of the Southern right whale, a quantitative analysis , 1982, Animal Behaviour.

[11]  Peggy L. Edds,et al.  Vocalizations of the Blue Whale, Balaenoptera musculus, in the St. Lawrence River , 1982 .

[12]  Christopher W. Clark,et al.  The sounds of the bowhead whale, Balaena mysticetus, during the spring migrations of 1979 and 1980 , 1984 .

[13]  M. Cynader,et al.  Sensitivity of cat primary auditory cortex (Al) neurons to the direction and rate of frequency modulation , 1985, Brain Research.

[14]  Gregory K. Silber,et al.  The relationship of social vocalizations to surface behavior and aggression in the Hawaiian humpback whale (Megaptera novaeangliae) , 1986 .

[15]  K. E. Moore,et al.  The 20-Hz signals of finback whales (Balaenoptera physalus). , 1987, The Journal of the Acoustical Society of America.

[16]  Richard Lippmann,et al.  Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[17]  Hsiao-Wuen Hon,et al.  An overview of the SPHINX speech recognition system , 1990, IEEE Trans. Acoust. Speech Signal Process..

[18]  Hal Whitehead,et al.  Click rates from sperm whales , 1990 .

[19]  Herbert L. Roitblat,et al.  Recognizing successive dolphin echoes with an integrator gateway network , 1991, Neural Networks.

[20]  N. Ramani,et al.  Fish detection and identification using neural networks-some laboratory results , 1992 .

[21]  Joydeep Ghosh,et al.  A neural network based hybrid system for detection, characterization, and classification of short-duration oceanic signals , 1992 .

[22]  P L Tyack,et al.  A quantitative measure of similarity for tursiops truncatus signature whistles. , 1993, The Journal of the Acoustical Society of America.

[23]  Thierry Aubin,et al.  ON THE EXTRACTION OF SOME TIME DEPENDENT PARAMETERS OF AN ACOUSTIC SIGNAL BY MEANS OF THE ANALYTIC SIGNAL CONCEPT. ITS APPLICATION TO ANIMAL SOUND STUDY , 1994 .

[24]  Christopher W. Clark,et al.  Application of Navy IUSS for whale research , 1994 .

[25]  J R Potter,et al.  Marine mammal call discrimination using artificial neural networks. , 1994, The Journal of the Acoustical Society of America.

[26]  B Pinkowski.  Robust Fourier descriptors for characterizing amplitude-modulated waveform shapes. , 1994, The Journal of the Acoustical Society of America.

[27]  Andrew Taylor.  Bird flight call discrimination using machine learning , 1995 .

[28]  Christopher W. Clark,et al.  SPATIAL DISTRIBUTION, HABITAT UTILIZATION, AND SOCIAL INTERACTIONS OF HUMPBACK WHALES, MEGAPTERA NOVAEANGLIAE, OFF HAWAI'I, DETERMINED USING ACOUSTIC AND VISUAL TECHNIQUES , 1995 .

[29]  J. Hildebrand,et al.  Blue and fin whales observed on a seafloor array in the northeast pacific. , 1995, The Journal of the Acoustical Society of America.

[30]  P. O. Thompson,et al.  UNDERWATER SOUNDS OF BLUE WHALES, BALAENOPTERA MUSCULUS, IN THE GULF OF CALIFORNIA, MEXICO , 1996 .

[31]  Julie A. Rivers,et al.  BLUE WHALE, BALAENOPTERA MUSCULUS, VOCALIZATIONS FROM THE WATERS OFF CENTRAL CALIFORNIA , 1997 .

[32]  K. Stafford,et al.  Long-range acoustic detection and localization of blue whale calls in the northeast Pacific Ocean. , 1998, The Journal of the Acoustical Society of America.

[33]  Adrian E. Raftery,et al.  Estimating Bowhead Whale Population Size and Rate of Increase from the 1993 Census , 1998 .

[34]  David E. Bain,et al.  SEASONAL VARIATION IN RECEPTION OF FIN WHALE CALLS AT FIVE GEOGRAPHIC AREAS IN THE NORTH PACIFIC , 1998 .

[35]  M. Merzenich,et al.  Optimizing sound features for cortical neurons. , 1998, Science.