Newborn babies no matter how cute they look, once they start crying it becomes a struggle. Firstly we don’t understand why the baby is crying. Secondly, we don’t know how to make him quiet. Thirdly every person around us gives us a look that says the baby is crying because of you.
Why is the baby crying?
A group of US-based researchers has now found out a way that could answer your first question- why the baby is crying. They have developed an artificial intelligence based system that is capable of telling the difference between a usual cry and an abnormal cry.
The researchers have developed a system that could tell whether the baby is crying because of hunger, illness, or some other reason. They have also published a research paper in the IEEE/CAA journal of Automatica Sinica (JAS).
Each baby is different, then how??
Although every baby is different and unique in its own way, there are some traits in every baby that mark them similar. Just like every person is capable of vision only with his eyes or of smelling only with his nose, in the same way, some traits helped the researchers mark the similarity.
Similar source of distress show similar features. For example, when a baby is crying, it would show some particular feature, or when he is hungry, he will show some trait. This allowed the researches to map them and conclude the analysis resulting in a near-successful system.
The algorithm behind the cry-detection
The researchers used algorithms based on the automatic speech recognition system to detect and recognize the features of infant cries. The team used a compressed sensing technique to analyze the enormous data created by the numerous calls of the babies.
Compressed sensing is a process by which the researchers reconstructed a signal that was based on the sparse data. This is especially useful when sounds are recorded in noisy environments. The researchers specially chose this environment because this is where babies often cry.
To understand and analyze things in a better manner, researchers designed a new cry language recognition algorithm. This algorithm is capable of distinguishing the meaning of both normal and abnormal cry signals in a noisy environment.
people can use this algorithm in a broader sense to recognize and classify various cry features and better understand why the babies are crying and how urgent the cry is.
What the researchers say
“Like a special language, there are lots of health-related information in various cry sounds. The differences between sound signals actually carry the information,” said Lichuan Liu, corresponding author.
Liu further added that “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 the information in it.”
“The ultimate goals are healthier babies and less pressure on parents and caregivers,” added Liu.
Researchers basically developed this syetem to help new parents to understand the reason behind the cry. At times of distress, it is better to have technology give us a solution rather than being stuck at the place and experiment with the various solutions we think might be possible.