Researchers from the University of Michigan are using artificial intelligence (AI) to better understand what a dog’s barking communicates about whether it is feeling playful or angry.

They are investigating whether artificial intelligence could correctly determine a dog’s age, sex, and breed based on its bark. Scientists, according to the BBC, have been able to make progress towards decoding dog communication using existing computer models trained on human speech.

“Advancements in artificial intelligence can be used to revolutionize our understanding of animal communication,” said University of Michigan AI Lab head Rada Mihalcea.

“Our research opens a new window into how we can leverage what we’ve built so far in speech processing to begin to understand the manifestations of dog barking.”

Artificial intelligence has allowed great strides to be made in understanding the details of speech.

AI-powered systems are used to distinguish nuances in pitch, depth and pronunciation, which in turn enables technologies such as voice recognition software.

They have reached this level of sophistication by being trained on a huge number of real human voices.

What is this Lassie?

However, there is no dog database that scientists can use to compare each bark.

“Animal vocalizations are practically much more difficult to request and record,” pointed out Artem Abzaliev, who led the study.

His team set out to find out if scientists could overcome this lack of data.

So his team collected the barks, growls and whines of 74 dogs of different breeds, ages and sexes, in a variety of contexts.

They then fed that data into a machine-learning program, a type of algorithm that identifies patterns in large data sets, that was designed to analyze human speech.

And they found it also did a good job of hearing what the dogs were trying to communicate.

On average, the researchers found their model to be 70% accurate in various tests.

“This is the first time that techniques optimized for human speech have been created to help decode animal communication,” said Ms Mihalcea.

“Our results show that sounds and patterns derived from human speech can serve as a basis for analyzing and understanding the patterns of other sounds, such as animal vocalizations.”

The researchers say their findings could have “significant implications” for animal welfare.
They suggest that a better understanding of the nuances of the various noises animals make could improve the way humans interpret and respond to their emotional and physical needs.