Pedigree chums at Science Daily.
A team at the Eötvös Loránd University in Hungary has shown that Computer programs may be the most accurate tool for studying acoustic communications amongst animals. The team led by Csaba Molnár has produced research which shows that a new piece of software is able to classify dog barks according to different situations and even identify barks from individual dogs.
The software analyzed more than 6000 barks from 14 Hungarian sheepdogs (Mudi breed) in six different situations: ‘stranger’, ‘fight’, ‘walk’, ‘alone’, ‘ball’ and ‘play’.
The software correctly classified the barks in 43 percent of cases. The best recognition rates were achieved for ‘fight’ and ‘stranger’ contexts, and the poorest rate was achieved when categorizing ‘play’ barks. These findings suggest that the different motivational states of dogs in aggressive, friendly or submissive contexts may result in acoustically different barks. The software could also reliably identify the barks of individual dogs. It also appears that certain barks are common and could constitute a universal language.
This seems to open up intriguing possibilities of the use of computers in the study of animal behaviour.
On a more whimsical level I wonder if this could ever lead to the commercial production of one of those wizzy electronic translators things for aid in interpreting dog speak (or perhaps mood).
Might be useful to have an alarm system that activates a warning if it detects an aggressive / fight bark, especially if related to 'stranger'.
Might be a good idea to turn it off during PMQ’s though. Batteries don’t last forever.