As most parents already know, differentiating between a baby's cries for food, tiredness, wetness or if it simply needs some care and attention, can be a real guessing game. Many people go through these motions, but few have truly mastered them.
What can be even trickier is knowing when a baby, who solely relies on its facial movements and cries to communicate, is becoming, or already is, sick.
This is where a group of researchers in the United States have come in. They have created a new artificial intelligence (AI) method that can identify and distinguish between regular cry signals, and cries in distress - for example due to an infant's illness.
Every parents' dream!
An algorithm to help parents distinguish baby cry signals.
Not only will this assist parents at home to quickly know what their baby needs, it also promises to be useful in healthcare environments. Doctors may also be able to use the device to discern cries amongst sick children.
With experience, health care workers and parents can quite easily and accurately tell what a baby needs depending on the sound they make when they cry.
Granted, all babies' cries are unique; however, they do still share common features when the issue is the same - for example if a baby has the colic.
However, when it comes to new parents, and when time is critical, identifying the hidden patterns in the cry signal can be a major challenge.
This is where the AI device can help speed up and facilitate the process.
How does the AI device work?
A specific algorithm based on automatic speech recognition is used in the new research. The algorithm detects and recognizes the different features in an infant's cries.
The research team used compressed sensing to analyze and classify these signals, which helped process the amount of data efficiently.
Compressed sensing is a process that reconstructs a signal based on little data and is specifically useful when sounds are recorded in noisy environments, the typical space where babies cry.
This research was published in the May issue of IEEE/CAA Journal of Automatica Sinica (JAS), a joint publication of the IEEE and the Chinese Association of Automation.
The researchers designed an algorithm that differentiates critical and non-critical cries of babies in noisy environments.
Lichuan Liu, Associate Professor and the author and conductor of the research, says, "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. To recognize and leverage the information, we have to extract the features and then obtain the information in it."
The hope for the future is that these findings could be applied to a number of medical care circumstances where experience is heavily relied upon.
"The ultimate goals are healthier babies and less pressure on parents and care givers," says Liu.
"We are looking into collaborations with hospitals and medical research centers, to obtain more data and requirement scenario input, and hopefully we could have some products for clinical practice," she adds.