Décomposition parcimonieuse des chants de cétacés pour leur suivi

Décomposition parcimonieuse des chants de cétacés pour leur suivi

Yann Doh Joseph Razik  Sébastien Paris  Olivier Adam  Hervé Glotin 

Equipe DYNI, Laboratoire de Sciences de l’Information et des Systèmes (LSIS), CNRS UMR 7296, Université du Sud Toulon-Var, avenue de l’Université,F-83957 La Garde

IUF, Institut Universitaire de France, 103, bd Saint-Michel, F-75005 Paris

Equipe DYNI, Laboratoire de Sciences de l’Information et des Systèmes (LSIS),ENSAM, CNRS UMR 7296, Aix-Marseille Université, Jardin du Pharo,58 bd Charles Livon, F-13284 Marseille

Lutheries Acoustique Musicale (LAM), Institut Jean Le Rond d’Alembert,CNRS UMR 7190, 11 rue de Lourmel, F-75015 Paris

Equipe Bioacoustique, Centre de Neurosciences Paris Sud, CNRS UMR 8195,Université Paris Sud Orsay, F-91405 Orsay cedex

Corresponding Author Email: 
yanndoh.m2@gmail.com
Page: 
219-242
|
DOI: 
https://doi.org/10.3166/TS.30.219-242
Received: 
N/A
| |
Accepted: 
N/A
| | Citation

OPEN ACCESS

Abstract: 

Male humpback whales emit songs during the breeding season. These songs are made with successive vocalizations called sound units. The study of these songs is based on the classification of these sound units, especially to extract the song theme of the singers in a specific area during a specific season. Recently, some approaches are proposed for automatic classification of these sound units. This paper introduces the sparse coding as a robust unsupervised classifier to generate efficient time-frequency representation of the calls of the whale. Secondly, the subunit shows to be interesting to analyze the evolution of the humpback whale songs during two years. It is statistically shown that the shortest units are the most stable (occurring with similar time frequency shape across the two years), while the longest units are evolving from one year to one other.

RÉSUMÉ

Au cours de la période de reproduction, les baleines à bosse mâles émettent des vocalises organisées et, pour certaines, répétées formant ainsi le leitmotiv d’un chant. Principalement, dans le but de mieux appréhender le comportement de ces baleines et notammen les interactions entre individus (mâle/mâle, mâle/femelle), plusieurs études sont actuellement menées sur ces chants. Dans cette étude, nous nous intéressons aux unités sonores, vocalises séparées par 2 silences, qui composent ces chants, à leurs récurrences, et à leurs structurations. Cependant, tous ces paramètres dépendent de l’année et du lieu d’enregistrement. Des travaux antérieurs ont souligné la nécessité de méthodes objectives pour la classification de ces unités sonores. L’analyse détaillée des vocalisations a montré que les caractéristiques d’une unité peuvent changer brusquement pendant toute sa durée, ce qui les rend difficiles à caractériser et à grouper systématiquement. Cet article propose un codage parcimonieux des chants afin de déterminer leurs composantes stables de celles qui varient, pour différentes échelles de temps. Une définition de la complexité du code est également proposée afin de séparer les composantes du chant du bruit mer. Notre méthode est illustrée sur un chant précédemment analysé. Les ré-sultats sont donnés pour le classement d’unités sonores et aussi de sous-unités sonores, notion que notre équipe a introduite précédemment. Cette étude montre statistiquement que les codes les plus courts sont les plus stables et surviennent avec une fréquence similaire sur deux années consécutives, tandis que les plus longues unités sont clairement différentes.

Keywords: 

sparse coding, humpback whale, sound units

MOTS-CLÉS

codage parcimonieux, baleine à bosse, unités sonores

1. Introduction
2. Matériel Et Méthode
3. Corrélation MFCC/codes Parcimonieux
4. Estimation De La Complexité Du Dictionnaire
5. Résultats
6. Discussion
7. Conclusion
  References

Abbot T. A., Premus V. E., Abbot P. A., Mayer O. W. (2012). Receiver operating characteristic for a spectrogram correlator-based humpback whale detector-classifier. J. Acoust. Soc. Am., vol. 132, no 3, p. 1502-1510.

Adam O., Cazau D., Gandilhon N., Fabre B., Laitman J. T., Reidenberg J. (2013). New acoustic model for humpback whale sound production. Journal of Applied Acoustics, vol. 74, no 10, p. 1182–1190.

Anden J., Mallat S. (2011). Multiscale Scattering for Audio Classification. In ISMIR p. 657–662.

Au W. W. L., Lammers M. O., Stimpert A., Schotten M. (2005). The temporal characteristics of humpback whale songs. J. Acoust. Soc. Am., vol. 118, no 3, p. 1940.

Baker C., Herman L. (1984). Aggressive behavior between humpback whale (megaptera novaeangliae) wintering in hawaiian waters. Canadian Journal of Zoology, vol. 62, p. 1922–1937.

Baumgartner M. F., Mussoline S. E. (2011). A generalized baleen wale call detection and classification system. J. Acoust. Soc. Am., vol. 129, p. 2889–2902.

Beyer K. S., Goldstein J., Ramakrishnan R., Shaft U. (1999). When is ”nearest neighbor”meaningful? In Proc. of the 7th international conference on database theory (icdt), p. 217–235. Springer-Verlag London.

Cazau D., Adam O., Laitman J. T., Reidenberg J. S. (2013). New understanding the intentional acoustic behavior of humpback whales: a production-based approach. J. Acoust. Soc. Am., vol. 143, no 3, p. 2268–2273.

Clapham P. J., Mattila D. K. (1990). Humpback whale songs as indicators of migration routes. Marine Mammal Science, vol. 6, no 2, p. 155–160.

Clark C. W., Clapham P. J. (2004). Acoustic monitoring on a humpback whale (megaptera novaeangliae) feeding ground shows continual singing into late spring. Proceedings - Royal Society of London. Biological sciences, vol. 271, no 1543, p. 1051–1057.

Darling J., Bérubé M. (2001). Interactions of singing humpback whales with other males. Marine Mammal Science, vol. 17, no 3, p. 570–584.

Davis S., Nermelstein P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans ASSP, vol. 28, p. 357–366.

Flandrin P., Baraniuk R. G., Michel O. (1994). Time-frequency complexity and information. In Ieee international conference on acoustics, speech, and processing, vol. 3, p. 329–332.

Frankel A., Clark C., Herman L., Gabriele C. (1995). Spatial distribution, habitat utilization and social interactions oh humpback whales, megaptera novaeangliae, of hawaii, determined using acoustic and visual techniques. Canadian Journal of Zoology, vol. 73, p. 1134–1146.

Gillepsie D. (2004). Detection and classification of right whale calls using an edge detector operating on a smoothed spectrogram. Can. Acoust., vol. 32, p. 39-47.

Glotin H., Gauthier L., Pace F., Benard F., Adam O. (2008). New automatic classification for humpback whale songs. In P. university, ONR (Eds.), Passive 08, p. 93.

Glotin H., Sueur J., Artière T., Adam O., Razik J. (2013). Sparse coding for scaled bioacoustics: From Humpback whale songs evolution to forest soundscape analyses. J. Acoust. Soc. Am.,vol. 133, no 5, p. 3311–3311.

Gravier G. (2010). Spro: a free speech signal processing toolkit. (Vers. 5.0. https://gforge.inria.fr/projects/spro)

Harris J. G., Skowronski M. D. (2006). Automatic speech processing methods for bioacoustics signal analysis: a case study of cross-disciplinary acoustic research. In Icassp, vol. 5, p. 793–796.

Helweg D. A. (1996). Geographic and temporal variation in songs of humpback whales. J. Acoust. Soc. Am., vol. 100, no 4, p. 2609.

Kullback S., Leibler R. (1951). On information and sufficiency. Annals of Mathematical Statistics, vol. 22, no 1, p. 79–86.

Madhsudhana S. K., Oleson E. M., Soldevilla M. S., Roch M. A., Hildebrand J. A. (2008). Frequency based algorithm for robust contour extraction of blue whale b and d calls. In Proc. of the ieee oceans, kobe, japan, vol. 3, p. 8.

Mairal J., Bach F., Ponce J., Shapiro G. (2009). Online dictionary learning for sparse coding. ICML, p. 689–696.

Mallawaarachchi A., Onga S. H., Chitre M., Taylor E. (2008). Spectrogram denoising and automated extraction of the fundamental frequency variation of dolphin whistles. J. Acoust. Soc. Am., vol. 124, p. 1159–1970.

Mazhar S., Ura T., Bahl R. (2008). An analysis of humpback whale songs for individual classification. J. Acoust. Soc. Am., vol. 123, no 5, p. 3774.

Medrano L., Salinas M., Salas I., Guevara P. L. D., Agayo A., Jacobsen J., Baker C. S. (1994). Sex identification of humpback whales, megaptera novaeangliae, on the wintering grounds of the pacific ocean. Canadian Journal of Zoology, vol. 72, p. 1771–1774.

Mellinger D. K., Clark C. W. (2000). Recognizing transient low-frequency whale sounds by spectrogram correlation. J. Acoust. Soc. Am., vol. 107, p. 3518–3529.

Mercado III E., Kuh A. (1998). Classification of humpback whale vocalizations using a selforganizing neural network. In Ieee world congress on computational intelligence, vol. 2, p. 1584–1589.

Miksis-Olds J., Buck J., Noad M., Cato D., Stokes M. (2008). Information theory analysis of australian humpback whale song. J. Acoust. Soc. Am., vol. 124, p. 2385–2393.

Noad M., Cato D., Bryden M., Jenner M., Jenner K. (2000). Cultural revolution in whale songs. Nature, London, vol. 408, p. 537.

Oswald J. N., Rankin S., Barlow J., Lammers M. O. (2007). A tool for real-time acoustic species identification of delphinid whistles. J. Acoust. Soc. Am., vol. 122, p. 587–595.

Pace F., White P., Adam O. (2009). Characterisation of sound subunits for humpback whale song analysis. In 4th international workshop on detection and localization of marine mammals using passive acoustics, p. 56.

Pace F., Benard F., Glotin H., Adam O., White P. (2010, november). Subunit definition and analysis for humpback whale classification. Journal of Applied Acoustics, vol. 71.

Pace F., White P. R., Adam O. (2011). Classification of humpback whale (megaptera novaeangliae) calls using hidden markov models. In 5th international workshop on detection, classification, localization, and density estimation of marine mammals using passive acoustics, p. 29.

Payne R. S., McVay S. (1971). Songs of humpback whales. Science, vol. 173, no 3997, p. 585–597.

Picot G., Adam O., Bergounioux M., Glotin H., Mayer F. (2008). Automatic prosodic clustering of humpback whales song. In I. explorer (Ed.), Passive 08, p. 6.

Rabiner L., Huang B. H. (1993). Fundamentals of speech recognition. Englewood Cliffs, NJ, Prentice Hall.

Reidenberg J. S., Laitman J. T. (2007). Discovery of a low frequency sound source in mysticeti (baleen whales): Anatomical establishment of a vocal fold homolog. Anat. Rec., vol. 290,p. 745–759.

Rickwood P., Taylor A. (2008). Methods for automatically analyzing humpback song units. J. Acoust. Soc. Am., vol. 123, no 3, p. 1763–1772.

Shannon C. (1948). A mathematical theory of communication. Bell System Technical Journal, vol. 27, p. 379–423,623–656.

Shapiro A. D., Wang C. (2009). A versatile pitch tracking algorithm: from human speech to killer whale vocalizations. J. Acoust. Soc. Am., vol. 126, p. 451–459.

Suzuki P., Buck J. R., Tyack P. L. (2006). Information entropy of humpback whale songs. J. Acoust. Soc. Am., vol. 119, no 3, p. 1849–1866.

Tyack P. (1981). Interactions between singing hawaiian humpback whales and conspecifics nearby. Behavioral Ecology and Sociobiology, vol. 8, no 2, p. 105–116.

Urazghildiiev I. R., Clark C. W. (2006). Acoustic detection of north atlantic right whale contact calls using the generalized likelihood ratio test. J. Acoust. Soc. Am., vol. 120, p. 1956–1963.

Winn H., Winn L. (1978). The song of the humpback whale megaptera novaeangliae in the west indies. Mar. Biol., vol. 47, p. 97–114.