Abstract
In this study we analyzed the possible context-specific and individual-specific features of dog barks using a new machine-learning algorithm. A pool containing more than 6,000 barks, which were recorded in six different communicative situations was used as the sound sample. The algorithm’s task was to learn which acoustic features of the barks, which were recorded in different contexts and from different individuals, could be distinguished from another. The program conducted this task by analyzing barks emitted in previously identified contexts by identified dogs. After the best feature set had been obtained (with which the highest identification rate was achieved), the efficiency of the algorithm was tested in a classification task in which unknown barks were analyzed. The recognition rates we found were highly above chance level: the algorithm could categorize the barks according to their recorded situation with an efficiency of 43% and with an efficiency of 52% of the barking individuals. These findings suggest that dog barks have context-specific and individual-specific acoustic features. In our opinion, this machine learning method may provide an efficient tool for analyzing acoustic data in various behavioral studies.
Similar content being viewed by others
References
Au WW (1994) Comparison of sonar discrimination: dolphin and an artificial neural network. J Acoust Soc Am 95:2728–2735
Au WW, Andersen LN, Rasmussen R, Roitblat HL, Nachtigall PE (1995) Neural network modeling of a dolphin’s sonar discrimination capabilities. J Acoust Soc Am 98:43–50
Bergeron BP (2003) Bioinformatics computing. Prentice-Hall, New York
Bogacz R, Brown MW (2003) Comparison of computational models of familiarity discrimination in the perirhinal cortex. Hippocampus 13:494–524
Burghardt T, Calic J (2006) Analysing animal behaviour in wildlife videos using face detection and tracking. IEEE, NY, Proc Vis Image Signal Process 153:305–312
Burghardt T, Thomas B, Barham PJ, Calic J (2004) Automated visual recognition of individual African penguins. In: Proceedings of Fifth International Penguin Conference, Ushuaia, September 2004
Cabral G, Pachet F, Briot J-P (2005) Automatic X traditional descriptor extraction: The case of chord recognition. In: Proceedings of the 6th international conference on music information retrieval (ISMIR’2005), London, September 2005
Calic J, Campbell N, Calway A, Mirmehdi M, Burghardt T, Hannuna S, Kong C (2005) Towards intelligent content based retrieval of wildlife videos. In: Proceedings of the Sixth WIAMIS, Montreux, April 2005
Cohen JA, Fox MW (1976) Vocalizations in wild canids and possible effects of domestication. Behav Processes 1:77–92
Defréville B, Roy P, Rosin C, Pachet F (2006) Automatic recognition of urban sound sources. In: Proceedings of the 120th AES Conference, Athens
Feddersen-Petersen DU (2000) Vocalization of European wolves (Canis lupus lupus L.) and various dog breeds (Canis lupus f. fam.). Arch Tierz Dummerstorf 43:387–397
Fielding AH (1999) Machine learning methods for ecological applications. Kluwer Academic Publishers, New York
Fitch WT, Neubauer J, Herzel H (2002) Calls out of chaos. The adaptive significance of nonlinear phenomena in mammalian vocal production. Anim Behav 63:407–418
Frommolt K-H, Goltsman ME, MacDonald DW (2003) Barking foxes, Alopex lagopus: field experiments in individual recognition in a territorial mammal. Anim Behav 65:509–518
Gerhardt HC (1992) Multiple messages in acoustic signals. Semin Neurosci 4:391–400
Hatzivassiloglou V, Duboué PA, Rzhetsky A (2001) Disambiguating proteins, genes, and RNA in text: a machine learning approach. Bioinformatics 17(Suppl. 1):97–106
Hauser MD (1996) The evolution of communication. MIT Press, Cambridge
Holekamp KE, Boydston EE, Szykman M, Graham I, Nutt KJ, Birch S, Piskiel A, Singh M (1999) Vocal recognition in the spotted hyena and its possible implications regarding the evolution of intelligence. Anim Behav 58:383–395
King RD, Hirst JD, Sternberg MJE (1993) New approaches to QSAR: neural networks and machine learning. Perspect Drug Discov Des 1:279–290
King RD, Muggleton S, Lewis RA, Sternberg MJE (1992) Drug design by machine learning: the use of inductive logic programming to model the structure-activity relationships of trimethoprim analogues binding to dihydrofolate reductase. PNAS 89:11322–11326
King RD, Sternberg MJE (1990) Machine learning approach for the prediction of protein secondary structure. J Mol Biol 216:441–457
Kohavi R, Sommerfield D (1995) Feature subset selection using the wrapper method: Overfitting and dynamic search space topology, First International Conference on Knowledge Discovery and Data Mining (KDD-95), Montreal
Koza J (1992) Genetic Programming: on the programming of computers by means of natural selection. MIT Press, Cambridge
Kremliovsky M, Kadtke J, Inchiosa M, Moore P (1998) Characterization of dolphin acoustic echo-location data using a dynamical classification method. Int J Bifurcat Chaos 8:813–823
Manser MB, Seyfarth RM, Cheney DL (2002) Suricate alarm calls signal predator class and urgency. Trends Cogn Sci 6:55–57
Mitchell TM (2005) Using machine learning and cognitive modeling to understand the fMRI measured brain activation underlying the representations of words and sentences. In: Proceedings of collaborative research computational neuroscience workshop, Arlington
Molnár Cs, Pongrácz P, Dóka A, Miklósi Á (2006) Can humans discriminate between dogs on the base of the acoustic parameters of barks? Behav Processes 73:76–83
Monceaux J, Pachet F, Amadu F, Roy P, Aymeric Z (2005) Descriptor-based spatialization. In: Proceedings of AES conference 2005, Athens
Morton ES (1977) On the occurrence and significance of motivation-structural rules in some bird and mammal sounds. Am Nat 111:855–869
Muggleton S, King RD, Sternberg MJE (1992) Protein secondary structure prediction using logic. Protein Eng 5:647–657
Owren MJ, Rendall D (2003) Salience of caller identity in rhesus monkey (Macaca mulatta) coos and screams: perceptual experiments with human (Homo sapiens) listeners. J Comp Psychol 117:380–390
Obach M, Wagner R, Werner H, Schmidt H-H (2001) Modeling population dynamics of aquatic insects with artificial neural networks. Ecol Modell 146:207–217
Pachet F, Zils A (2004) Automatic extraction of music descriptors from acoustic signals. In: Proceedings of ISMIR 2004, Barcelona
Pachet F, Roy P (2007) Exploring billions of audio features. In: Proceedings of CBMI (Content-Based Multimedia Indexing), Bordeaux, France
Pongrácz P, Molnár Cs, Miklósi Á, Csányi V (2005) Human listeners are able to classify dog barks recorded in different situations. J Comp Psychol 119:136–144
Pongrácz P, Molnár Cs, Miklósi Á, Csányi V (2006) Human understanding of dog barks: why we did not know what we knew all along? Appl Anim Behav Sci 100:228–240
Recknagel F (2001) Applications of machine learning to Ecol Model. Ecol Modell 146:303–310
Schassburger RM (1993) Vocal communication in the timber wolf, Canis lupus, Linnaeus. Advances in ethology (No. 30). Paul Parey Publishers, Berlin
Schleiter IM, Obach M, Borchardt D, Werner H (2001) Bioindication of chemical and hydromorphological habitat characteristics with benthic macro-invertebrates based on artificial neural networks. Aquatic Ecol 35:147–158
Seyfarth RM, Cheney DL, Marler P (1980) Monkey responses to three different alarm calls: evidence of predator classification and semantic communication. Science 210:801–803
Slobodchikoff CN, Kiriazis J, Fischer C, Creef E (1991) Semantic information distinguishing individual predators in the alarm calls of Gunnison’s prairie dogs. Anim Behav 42:713–719
Stockwell DRB (2006) Improving ecological niche models by data mining large environmental datasets for surrogate models. Ecol Modell 192:188–196
Tembrock G (1976) Canid vocalizations. Behav Processes 1:57–75
Witten I, Eibe F (1999) Data Mining, Morgan Kaufmann Publishers, San Francisco
Yin S (2002) A new perspective on barking in dogs (Canis familiaris). J Comp Psychol 119:189–193
Yin S, McCowan B (2004) Barking in domestic dogs: context specificity and individual identification. Anim Behav 68:343–355
Zhang L, Samaras D, Klein N, Tomasi D, Cottone L, Leskovjan A, Volkow N, Goldstein R (2005a) Exploiting temporal information in functional magnetic resonance imaging brain data, In: Proceedings of MICCAI, Palm Springs, pp 679–687
Zhang L, Samaras D, Tomasi D, Volkow N, Goldstein R (2005b) Machine Learning for clinical diagnosis from functional magnetic resonance imaging. In: IEEE proceedings of CVPR, San Diego, pp 1211–1217
Acknowledgments
The authors are thankful to the members of the MEOE Magyar Mudi Klub for their assistance with the sound recordings. We also wish to thank Celeste Pongrácz for checking our English in this paper. This study was funded by grants from the Hungarian NSF (OTKA) No. T047235.
Author information
Authors and Affiliations
Corresponding author
Additional information
We cite several conference proceedings because in computer science the conference proceedings are more important than in biology. For engineers, it is essential to show their colleagues that their product (e.g. software) is actually working, so in this field of science the main forums for scientific discussion are the conferences.
Rights and permissions
About this article
Cite this article
Molnár, C., Kaplan, F., Roy, P. et al. Classification of dog barks: a machine learning approach. Anim Cogn 11, 389–400 (2008). https://doi.org/10.1007/s10071-007-0129-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10071-007-0129-9