Scientists Developing AI Technology To Decipher Your Dog’s Barking

There is no dog owner out there who doesn’t wish to understand their pet’s bark! And now that artificial intelligence is evolving and expanding with each new day, it seems that this seemingly impossible feat can now become a reality.

A research team at the University of Michigan is now studying how exactly artificial intelligence can be used to help understand the way dogs communicate. The scientists are developing special AI tools that will ultimately help understand whether a dog’s bark is aggressive, or shows playful intentions. And that is not all – AI will help gather crucial information from the bark, such as the breed, age, and sex of the dog. 

“By using speech processing models initially trained on human speech, our research opens a new window into how we can leverage what we built so far in speech processing to start understanding the nuances of dog barks,” said Rada Mihalcea, director of the University of Michigan’s AI laboratory.

Throughout the course of the study, the team studied vocalizations from 74 different dogs, all in various contexts. They quickly realized that AI models that were originally trained on human speech could now be a great starting point to help train new AI systems made specifically to understand animal communication.

“There is so much we don’t yet know about the animals that share this world with us,” said Mihalcea. “Advances in AI can be used to revolutionize our understanding of animal communication, and our findings suggest that we may not have to start from scratch.”

Mihalcea also adds that all their findings indicate that “the sounds and patterns originating from human speech can form the basis for examining and comprehending the acoustic patterns of other sounds, including animal vocalizations”.

But even so, using AI to analyze dog communication is hindered, as there is still a lack of data available publicly.

“Animal vocalizations are logistically much harder to solicit and record,” said Artem Abzaliev, lead author of the study. “They must be passively recorded in the wild or, in the case of domestic pets, with the permission of owners.”

Besides this, scientists were also able to reuse a model that analyzed human speech. This helped them to “tap into” major voice-enabled technologies that can actually recognize spoken words and those speaking them.

“These models are able to learn and encode the incredibly complex patterns of human language and speech,” Abzaliev adds. “We wanted to see if we could leverage this ability to discern and interpret dog barks.”

What is more, according to the study the research will also have major implications for animal welfare. If we can understand dog vocalizations, it can help us respond better to the needs of our pets.