AI Can Now Translate a Babies Cries

placeholder image

Being a parent is not easy. Being a first time parent is scary. Not understanding what your newborn cries mean can be downright terrifying.

First time parents have so much to worry about and now scientists are trying to make things a bit easier. Not only for the parents, but for doctors as well.

Researchers at Northern Illinois University have created an algorithm that can help translate a babies cries. The method would distinguish between a normal whimper and an abnormal one.

Although each babies cry does vary a bit, most tend to share similar speech patterns. According to BBC, “The team developed an algorithm based on an already existing automatic speech recognition system to detect and recognize the features of infant cries along with a technique called compressed sensing – a process that is able to reconstruct a signal based on very sparse data, especially in environments with high levels of background noise.”

A database of infant cries allows the AI to pick up on the different features in their loudness, pitch and timbre.

For example, the “neh” sound correlates with hunger. While the “eh” sound generally means the baby needs to burp.

“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,” said Prof Lichuan Liu BBC reports.

Hopefully this would greatly assist the health of infants.

KOST 103.5 · Feel Good Los Angeles!
Listen Now on iHeartRadio