Parents who are wondering whether their crying baby is hungry, tired, or even in pain could soon be able to use a language acquisition algorithm which detects the reasons for the baby’s cries.
The new cry language acquisition algorithm has been developed to identify and distinguish between the normal signals of a crying baby, such as when the baby is tired or hungry and abnormal ones resulting from illness.
Understanding the needs of a crying baby
Lichuan Liu, the corresponding author and Associate Professor of Electrical Engineering and the Director of Digital Signal Processing Laboratory whose group conducted the research, explained: “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.”
How speech recognition helps
The algorithm is based on automatic speech recognition to recognise the features of infant cries. The team used compress sensing, a process that reconstructs a signal based on sparse data and when sounds are recorded in noisy environments. They designed a new cry language recognition algorithm which can distinguish what normal and abnormal cry sounds mean even in noisy environments.
According to Chinese Association of Automation, the algorithm is independent of the individual crying baby, which means it can be used broadly in practical scenarios.
Could the language acquisition algorithm be used in a clinical setting?
The researchers said they hope this study could help in other medical care circumstances, where currently the decision making relies on experience.
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 centers, to obtain more data and requirement scenario input, and hopefully we could have some products for clinical practice.”