Recognition of infant's emotions and needs from speech signals

Speech is not only a way for infants under one year of age to communicate with the outside world, but also the important information source to reflect their emotions and needs, as well as health status and mental level. In order to explore the intelligent machine technology for understanding infant's emotions and needs from speech signals, and therefore help parents in child rearing, this paper studied the signal processing and feature extraction of the above speeches. It seems that a high accuracy and reliable result couldn't be reached from the infant's speech signals only in dealing with multi kinds of emotions and needs. So an effective recognition approach considering the combined features of acoustic characteristics and rearing behaviors was proposed based on the self-adapting algorithm. Experiment results showed that most common emotions and needs of infants, such as happy, hungry, and sleepy states which reflect their typically physiological and psychological status in daily life, can be recognized correctly at a relatively high accuracy.