Grunt of the litter: scientists use AI to decode pig calls

Humans are trouncing each other at video games and chess. Artificial intelligence can be used to infer how pigs are feeling based on their grunts.

The pig translator could be used to automatically monitor animal wellbeing and pave the way for better livestock treatment on farms and elsewhere.

We have trained a program to decode pig grunts, but we need someone who wants to do it.

Briefer worked with an international team of colleagues to train a neural network to learn whether pigs were experiencing positive or negative emotions, using audio recordings and behavioural data from pigs in different situations.

In the journal Scientific Reports, the researchers describe how they used the artificial intelligence to analyse the pig calls. Most of the recordings came from farms and other commercial settings, but some came from experimental enclosures where pigs were given toys, food and unfamiliar objects to explore.

The scientists used a method to distinguish between positive and negative calls. Positive situations such as huddling with littermates, suckling their mothers, running about and being rejoined with the family, and negative situations such as piglet fights, crushing, castration and waiting in the abattoir were reflected in the different noises.

The researchers found that there were more high-pitched shrieks. Low-pitched grunts and barks were heard across the board, regardless of their situation. The short grunts were a good sign of porcine contentment.

There are clear differences in pig calls when looking at positive and negative situations. According to the researchers, the algorithm correctly classified 92% of the calls as positive or negative emotions. With more recordings, the pig translator may be able to learn more about the mental wellbeing of other animals.

The majority of animal welfare efforts focus on physical health, not the mental health of animals. Briefer and her colleagues believe that their algorithm can pave the way for new automated systems in the livestock industry that monitor sounds on farms and other sites to assess the animals' psychological wellbeing.