Classification of dog barks: a machine learning approach

Molnár, Csaba; Kaplan, Frédé́ric; Roy, Pierre; Pachet, François; Pongrácz, Péter; Dóka, Antal; Miklósi, Ádám

doi:10.1007/s10071-007-0129-9

Cited by 75 publications

(63 citation statements)

References 38 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it was successfully solved for 55.50 % of the bark cases. This is an improvement on the results presented in Molna´r et al (2008), where for six possible contexts the best model yielded a 43 % success rate. With an accuracy rate of 63 % for classifying three possible contexts, our results are similar to the findings reported by Yin and McCowan (2004).…”

Section: Discussionsupporting

confidence: 51%

“…Based on the initial parameter set used in Molna´r et al (2008), 29 acoustic measures were extracted from the bark samples with an automated Praat script, see Table 3 and Fig. 1.…”

Section: Sound Analysismentioning

confidence: 99%

“…As in Molna´r et al (2008), we classify barks into contexts and identify individual barks. Unlike Molna´r et al, we also investigate whether barks encode information about dog sex and age.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Comparing supervised learning methods for classifying sex, age, context and individual Mudi dogs from barking

et al. 2014

Self Cite

View full text Add to dashboard Cite

Barking is perhaps the most characteristic form of vocalization in dogs; however, very little is known about its role in the intraspecific communication of this species. Besides the obvious need for ethological research, both in the field and in the laboratory, the possible information content of barks can also be explored by computerized acoustic analyses. This study compares four different supervised learning methods (naive Bayes, classification trees, k-nearest neighbors and logistic regression) combined with three strategies for selecting variables (all variables, filter and wrapper feature subset selections) to classify Mudi dogs by sex, age, context and individual from their barks. The classification accuracy of the models obtained was estimated by means of K-fold cross-validation. Percentages of correct classifications were 85.13 % for determining sex, 80.25 % for predicting age (recodified as young, adult and old), 55.50 % for classifying contexts (seven situations) and 67.63 % for recognizing individuals (8 dogs), so the results are encouraging. The best-performing method was k-nearest neighbors following a A. Larranaga Student at the Universidad Alfonso X El Sabio, Av. Universidad, 1, 28691 Villanueva de la Canada, Madrid, Spain wrapper feature selection approach. The results for classifying contexts and recognizing individual dogs were better with this method than they were for other approaches reported in the specialized literature. This is the first time that the sex and age of domestic dogs have been predicted with the help of sound analysis. This study shows that dog barks carry ample information regarding the caller's indexical features. Our computerized analysis provides indirect proof that barks may serve as an important source of information for dogs as well.

show abstract

Section: Discussionsupporting

confidence: 51%

“…Based on the initial parameter set used in Molna´r et al (2008), 29 acoustic measures were extracted from the bark samples with an automated Praat script, see Table 3 and Fig. 1.…”

Section: Sound Analysismentioning

confidence: 99%

See 1 more Smart Citation

Comparing supervised learning methods for classifying sex, age, context and individual Mudi dogs from barking

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…Features such as the ones proposed by Schrader and Hammerschmidt (1997) are all within the reach of feature generation, meaning that the system can find these features or approximations thereof. In fact, feature generation has been shown to outperform approaches based on standard features in the context of animal vocalization (Molnár et al, 2008).…”

Section: B the Feature Generation Approachmentioning

confidence: 99%

Finding good acoustic features for parrot vocalizations: The feature generation approach

Giret

Roy²,

Albert

et al. 2011

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

A crucial step in the understanding of vocal behavior of birds is to be able to classify calls in the repertoire into meaningful types. Methods developed to this aim are limited either because of human subjectivity or because of methodological issues. The present study investigated whether a feature generation system could categorize vocalizations of a bird species automatically and effectively. This procedure was applied to vocalizations of African gray parrots, known for their capacity to reproduce almost any sound of their environment. Outcomes of the feature generation approach agreed well with a much more labor-intensive process of a human expert classifying based on spectrographic representation, while clearly out-performing other automated methods. The method brings significant improvements in precision over commonly used bioacoustical analyses. As such, the method enlarges the scope of automated, acoustics-based sound classification.

show abstract

“…In an early experiment, Yin and McCowan (2004) found that dog barks could be statistically attributed to individual callers (irrespective of production context) using a discriminant function analysis. Similarly, Molnár et al (2008) developed computer-based learning software, which categorised individual dogs on the basis of their barks. Human listeners, however, struggled to reliability discriminate between barks from dogs of the same breed , although the presentation of five-bark sequences did somewhat improve discrimination.…”

Section: Individual Recognitionmentioning

confidence: 99%