Infant cry detection algorithm

We have recently teamed up Rami Cohen of Technion, Israel Institute of Technology and Yizhar Lavner of Tel-Hai Academic College in order to incorporate their cry detection algorithm in one of the custom apps we are currently developing at our lab.

“The proposed algorithm is based on two main stages. The first stage involves feature extraction, in which pitch related parameters, MFC (mel-frequency cepstrum) coefficients and short-time energy parameters are extracted from the signal. In the second stage, the signal is classified using k-NN and later verified as a cry signal.”

Leave a Reply