Researchers at the University of Michigan are using artificial intelligence (AI) to learn more about the meaning behind a dog’s bark, including whether it is playful or angry.
Additionally, they are investigating whether AI might accurately determine the breed, age, and gender of a dog only by listening to its woofs.
By repurposing existing computer models trained on human speech, the scientists were able to make progress toward interpreting canine communication.
“Technological advancements in AI have the potential to completely transform our understanding of animal communication,” said Rada Mihalcea, director of the University of Michigan AI Laboratory.
“Our research opens a new window into how we can leverage what we have built so far in speech processing to start understanding the nuances of dog bark.”
Significant progress has been achieved in comprehending the nuances of speech thanks to AI.
Artificial intelligence (AI) systems are utilized to discern subtleties in tone, pitch, and accent, hence facilitating technologies like voice recognition software.
They were taught on a vast array of actual human sounds, which has allowed them to attain that degree of sophistication.
The study’s primary author, Artem Abzaliev, noted that recording animal vocalizations is logistically far more difficult.
His team’s goal was to find out if using human research as a springboard may help scientists overcome this data gap.
Thus, his group recorded 74 dogs’ barks, growls, and whimpers in a range of settings, from different breeds to different ages and sexes.
