A computer has been programmed to understand the quirks of a dog’s bark, including the context and the sound of each individual ‘voice’.
The team, led by Csaba Molnár from Eötvös Loránd University, Hungary, programmed computer algorithms to identify and differentiate the acoustic features of dog barks, classifying them according to different contexts and individual dogs. The software analysed more than 6,000 barks from 14 Hungarian sheepdogs (Mudi breed) in six different situations: ‘stranger’, ‘fight’, ‘walk’, ‘alone’, ‘ball’ and ‘play’.
The barks were recorded with a tape recorder before being transferred to the computer, where they were digitalised and individual bark sounds were coded, classified and evaluated.
In the first experiment looking at the classification of barks into different situations, the software correctly classified the barks in 43 per cent of cases. The best recognition rates were achieved for ‘fight’ and ‘stranger’ contexts, and the poorest rate was achieved when categorising ‘play’ barks. These findings suggest that the different motivational states of dogs in aggressive, friendly or submissive contexts may result in acoustically different barks.
In the second experiment looking at the recognition of individual dogs, the algorithm correctly classified the barks in 52 per cent of cases. The software could reliably discriminate among individual dogs while humans cannot, which suggests that there are individual differences in barks of dogs even though humans are not able to recognise them.
The authors concluded: ‘The promising results obtained strongly suggest that advanced machine learning approaches deserve to be considered as a new relevant tool for ethology.’
Reference: Molnar C et al (2008). Classification of dog barks: a machine learning approach. Animal Cognition (DOI 10.1007/s10071-007-0129-9)