Taiwanese researchers have come up with an app that can distinguish between varieties of crying sounds made by babies. They have developed the app named the Infant Cries Translator at the National Taiwan University Hospital, Yunlin.

The app can differentiate between four separate crying sounds. It records the sounds of babies and compares them against a huge database.

Researchers collected nearly 200,000 crying sounds from roughly 100 newborns over a time period of two years. They uploaded the sounds on an online database. Researchers, led by Chang Chuan-yu and Dr Chen Si-da analyzed the frequency of individual screams and this analysis helped them in distinguishing subtle differences in acoustics.

The app displays analysis of the cries of a baby on the phone of the user within 15 seconds. According to researchers, the app is 92% accurate in the case of infants below 2 weeks age. The app would help parents know when their child is hungry, in pain, sleepy, or has a wet diaper. The older the baby is, the analysis gets less accurate.

Chuan-yu said the Infant Cries Translator can distinguish between 4 different statuses of sounds of baby crying, which includes hunger, the diaper getting wet, sleepy and pain.

Chuan-yu added, “So far, according to the feedback from users, the accuracy of the app we've tested can reach 92% for babies under two weeks old. As for the babies under one or two months, the accuracy of the app can also reach up to 84 or 85%”. Chuan-yu said that in the case of four months old baby, the accuracy can touch 77%.