Most new parents will know the frustration of hearing their baby cry, without knowing whether it’s hungry, wet, tired, or even in pain.
Now, scientists have developed an artificial intelligence system that can tell babies’ cries apart.
The system, which was developed by researchers from the IEEE and the Chinese Association of Automation, could be an absolute game-changer for parents at home, as well as in healthcare settings.
While each baby’s cry is unique, they share some common features, which the researchers utilised when training the AI.
Dr Lichuan Liu, an author of the study, said: "Like a special language, there are lots of health-related information in various cry sounds.
“The differences between sound signals actually carry the information. These differences are represented by different features of the cry signals.”
In the study, the researchers designed a new algorithm that can distinguish the meanings of both normal and abnormal cry signals, even in noisy environments.
Importantly, the algorithm works across different babies, meaning it could not only be used by parents, by also by doctors to understand the meaning of cries from sick children.
Dr Liu added: “The ultimate goals are healthier babies and less pressure on parents and care givers.
“We are looking into collaborations with hospitals and medical research centres, to obtain more data and requirement scenario input, and hopefully we could have some products for clinical practice.”
