Scientists create AI Pig translator to decode emotions through pig calls

Scientists have “trained” a machine learning system to determine if a pig’s sounds are associated with a happy or negative emotion.

The new artificial-intelligence-based “pig translator,” which might be a game-changer in the field of animal behaviour, will provide insights into the well-being of pigs, particularly in farms and slaughterhouses.

Dr Elodie Briefer, animal behaviour and communication expert who co-led the study at the University of Copenhagen said, “We have trained the algorithm to decode pig grunts,”

“Now we need someone who wants to develop the algorithm into an app that farmers can use to improve the welfare of their animals.”

The study, which was published in the journal Scientific Reports, demonstrates how the researchers trained the algorithm to analyse acoustic fingerprints of 7,414 recordings of pig sounds collected from 411 individuals at different periods of their lives, including slaughter.

These recordings were made in both commercial and experimental environments.

The programme can tell whether a pig is happy or excited, or sad or distressed.

In emotionally positive situations, such as when piglets nurse from their mothers or when the family is being separated, vocalisations related with happiness or joy were recorded.

Short periods of social isolation, piglet fights, castration, handling, and waiting in the slaughterhouse were all negative experiences.
Researchers were able to decode a pattern that provided more information about what the pigs went through in different scenarios.