 |
 |
|
|
|
publications
| Classification of dog barks: a machine learning approach |
|
|
|
|
Molnar, C., Kaplan, F., Roy, P., Pachet, F., Pongracz, P., Doka, A. and Miklosi, A. (2008) Classification of dog barks: a machine learning approach, Animal Cognition, 11(3) : 389-400 |
|
Journal Reference
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. Keywords Acoustic communication - Dog barks - Machine learning - Genetic programming
Notes :
This paper has received a lot of media interest, with sometimes not very accurate accounts: "Computer Decodes Dog Communication" (ABC News); "Scientists decode dogspeak" (MSNBC); "Computer Translates Dog Barks" (FOXNews); "Comuter Learns Dogspeak: Programs Can Classify Dog Barks Better Than Humans, Study Shows" (Science Daily); "Computer can help your dog communicate" (Reuters); "Yap-lication unlocks canine moods" (BBC News); " Computer communicates with dogs" (Telegraph). Most of these headlines are overstatements of the actual results shown in the paper.
For clarification, the ethological aspects (gathering of data, interpretation of the results) of this work have been conduced by Molnar Csaba, Peter Pongracz and Adam Miklosi from the Eotvos Lorand University in Budapest. The machine learning study has been conducted by Frederic Kaplan with the help of Pierre Roy based on the EDS software developed by Francois Pachet and his team at Sony CSL Paris.
|
|
|
animalcogn ... |
|
|
|
|
|
|
|
|
|
|
|
)