Most adults know a crying baby is usually just trying to tell someone how they're feeling. But researchers at Brown University and the Women and Infants Hospital in Rhode Island believe there are underlying messages encoded within these cries. Based on previous research saying that these messages can speak of potential health problems, they've developed a tool that will try to decipher them.

"Cry is an early warning sign that can be used in the context of looking at the whole baby," Barry Lester, director of Brown's Center for the Study of Children at Risk, said in a press release.

Lester says that the basis for this research comes from the 1960s, when babies with a disorder called Cri du Chat (cry of the cat) syndrome, which is caused by a genetic abnormality similar to Downs syndrome, displayed distinct, higher-pitched cries. Even though these differences in cry were obvious to the human ear, researchers thought that maybe there were other, more subtle differences the human ear couldn't find. They would show up in differences in pitch and other acoustic features.

"There are lots of conditions that might manifest in differences in cry acoustics," Stephen Sheinkopf, assistant professor of psychiatry and human behavior at Brown, said. "For instance, babies with birth trauma or brain injury as a result of complications in pregnancy or birth or babies who are extremely premature can have ongoing medical effects. Cry analysis can be a noninvasive way to get a measurement of these disruptions in the neurobiological and neurobehavioral systems in very young babies."

The researchers developed a computer-based tool that could analyze intricate details in a baby's cry. By working in two phases, it first records cries in 12.5 millisecond frames during which each frame is analyzed based on a number of factors, including frequency characteristics, voicing, and acoustic volume. During the second phase, the computer analyzes all the data from the first phase, and then reduces the number of factors to those that are most useful. It also puts the frames back together and characterizes them as either an utterance — a single "wah" — or silence, which is the pause in-between utterances.

By analyzing these utterances for the time between each one, their pitch, and the way the pitch moves increasingly louder or lower, the computer is able to determine, based on a total of 80 factors, if there might be something wrong with the baby's health. For example, neurological deficits might alter a baby's ability to move their vocal chords. These changes would be picked up.

Sheinkopf, who specializes in developmental disorders hopes to use the tool to look for features that might allude to autism.

"We've known for a long time that older individuals with autism produce sounds or vocalizations that are unusual or atypical," Sheinkopf said. "So vocalizations in babies have been discussed as being useful in developing early identification tools for autism. That's been a major challenge. How do you find signs of autism in infancy?"


Lester M, Sheinkopf J, Silverman H, et al. A Flexible Analysis Tool for the Quantitative Acoustic Assessment of Infant Cry. Journal of Speech, Language, and Hearing Research. 2013.