Baby care technology invented for the millennials. Let’s talk about that.
Babies don’t cry wolf. A baby’s cry always means something is amiss.
But figuring out what’s wrong is a distressful process that can bring parents to tears!
Most parents learn to recognize different kinds of cries. But there are subtle differences that may escape even the instinctively tuned senses of a mother. Fortunately, technology has lent an ear.
Researchers have patented a system that can analyze a baby’s cry and identify its exact cause.
The system works by capturing the sound of crying and analyzing its spectral characteristics.
Based on the analysis, the system determines whether the baby is crying due to a basic need such as hunger or a special need such as being ill.
The system extracts a time-frequency characteristic of the sound and compares it with a database of time-frequency characteristics corresponding to different kinds of cries.
Based on the comparison, the particular basic need is identified.
The basic need may be hungry, sleepy/tired, discomfort, flatulent and wanting to belch.
If the crying sound is detected to be of special type, the time-frequency characteristic of the sound is fed to an artificial neural network, which is trained to identify a particular special need.
By converting a baby’s cry into adult-speak, this invention takes away a lot of guess-work from parenting and helps in providing the right response to soothe a crying baby. Who knows what could be next? Perhaps a translator for those goo-goo-ga-ga’s!
Patent Information
US 9,009,038
Method and system for analyzing digital sound audio signal associated with baby cry
Abstract
A method for analyzing a digital audio signal associated with a baby cry, comprising the steps of: (a) processing the digital audio signal using a spectral analysis to generate a spectral data; (b) processing the digital audio signal using a time-frequency analysis to generate a time-frequency characteristic; (c) categorizing the baby cry into one of a basic type and a special type based on the spectral data; (d) if the baby cry is of the basic type, determining a basic need based on the time-frequency characteristic and a predetermined lookup table; and (e) if the baby cry is of the special type, determining a special need by inputting the time-frequency characteristic into a pre-trained artificial neural network.
Inventors: Hong; Jon-Chao, Wu; Chao-Hsin, Chen; Mei-Yung
Applicant: National Taiwan Normal University
Appl. No.: 13/899,645
Filed: May 22, 2013
GIF file.
