AI: Talking with a Sus Domesticus
March 22, 2022
Humans have wanted to understand their fellow animals since the Garden of Eden. They have conducted research experiments to learn animal behavior with the possible hope of decoding the language of beasts. Following in the throes of past animal researchers, AI scientists might have cracked the code to talking with animals says The Guardian in: “Grunt Of The Litter: Scientists Use AI To Decode Pig Calls.”
Animal communication expert Dr. Elodie Briefer of the University of Copenhagen worked with an international team to develop an algorithm that decodes pig grunts. The team trained a neural network to decipher when swine experienced positive and negative emotions with audio recordings and behavioral data.
The researchers found:
“The scientists used the algorithm to distinguish calls linked to positive emotions from those linked to negative emotions. The different noises represented emotions across the spectrum and reflected positive situations, such as huddling with littermates, suckling their mothers, running about and being reunited with the family, to negative situations ranging from piglet fights, crushing, castration and waiting in the abattoir.
The researchers found that there were more high-pitched squeals in negative situations. Meanwhile, low-pitched grunts and barks were heard across the board, regardless of their predicament. Short grunts, however, were generally a good sign of porcine contentment.”
Dr. Briefer and her team discovered there’s a stark difference between positive and negative pig sounds. The algorithm correctly classified 92% of grunt recordings. The team hopes to expose the algorithm to more recordings with a broader emotion spectrum for further clarification and possibly communicate with other animals.
The pig translation algorithm could be employed in the meat industry to improve animals’ mental welfare. Dr. Temple Grandin revolutionized animals’ physical and mental wellbeing with her improvements to the meat industry, Dr. Briefer and her team could build on her research. They can do a whole lot more than PETA. In the meantime, we might be on our way to understanding pigs, but why do we still have trouble with automated phone systems?
Whitney Grace, March 22, 2022