AI could distinguish between different types of baby cries

Researchers in the US have designed a new cry language recognition algorithm that could help distinguish between normal baby cries and cries with more serious implications. Each baby’s cry is unique, but there are common features when they cry for the same reasons, and finding those patterns within the cry has been testing. This research uses an algorithm based on automatic speech recognition to recognise the features of infant cries to get a clearer idea of why a baby is crying. The researchers then analysed and classified those signals using compressed sensing to process big data more efficiently.
Researcher Lichuan Liu, Associate Professor of Electrical Engineering and the director of Digital Signal Processing Laboratory at Northern Illinois University, said: “Like a special language, there are lots of health-related information in various cry sounds. The differences between sound signals carry the information. These differences are represented by different features of the cry signals. To recognise and leverage the information, we have to extract the features and then obtain the information in it.”