A new computer-based tool analyzes the acoustic signal of a baby's cry to alert parents of health concerns. Picture:AFP
For parents hoping to decipher the subtle clues lurking in the cries of their baby, a new tool can help. Researchers at Brown University and Women & Infants Hospital in the US have devised a "cry analyzer" to detect slight variations in cries, mostly imperceptible to the human ear, but that serve as a "window into the brain," they said.
To parents, a baby's cry is a signal of hunger, pain, or wet diaper discomfort, for example. But to scientists, subtle acoustic features of a cry can hold important information about a baby's health.
The team has developed a new computer-based tool to perform finely tuned acoustic analyses of babies' cries. The goal is that the cry analyzer will lead to new ways for researchers and clinicians to use crying in identifying children with neurological problems or developmental disorders.
"There are lots of conditions that might manifest in differences in cry acoustics," said Stephen Sheinkopf, assistant professor of psychiatry and human behavior at Brown, who helped develop the new tool. "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 system operates in two phases. During the first phase, the analyzer separates recorded cries into 12.5-millisecond frames. Each frame is analyzed for several parameters, including frequency characteristics, voicing, and acoustic volume.
The second phase uses data from the first to give a broader view of the cry and reduces the number of parameters to those that are most useful, the researchers explained. The frames are put back together and characterized either as an utterance -- a single "wah" -- or silence, the pause between utterances. Longer utterances are separated from shorter ones and the time between utterances is recorded. Pitch, including the contour of pitch over time, and other variables can then be averaged across each utterance.
In the end, the system evaluates for 80 different parameters, each of which could hold clues about a baby's health.
"It's a comprehensive tool for getting as much important stuff out of a baby cry that we can," said Harvey Silverman, professor of engineering and director of Brown's Laboratory for Engineering Man/Machine Systems.
The project, announced July 11, is described in the Journal of Speech, Language and Hearing Research.