The Study of Baby Crying Analysis Using MFCC and LFCC in Different Classification Methods

Nowadays, there are so many researches about the baby crying detection for many purposes. The right interpretation of the crying baby is notable for the medical objective so caregiver knows how to treat baby well. Babies within the first three months of age use Dustan Baby Language (DBL) to communicate. Based on some researches, there are five words to express their needs, such as “Neh” (I am hungry), “Eh” (burp is needed), “Owh/Oah” (fatigue), “Eair/Eargghh” (cramps), “Heh” (physical discomfort; feel hot or wet). Beside that purpose, smart home technology implements baby crying detection for monitoring the baby. Several stages to detect crying baby are preprocessing, feature extraction, and classification. Popular feature extractions for voice or sound recognition are Mel Frequency Cepstral Coefficient (MFCC) and Linear Frequency Cepstral Coefficient (LFCC). In this study, both of that feature extraction have been analyzed to know the appropriate condition when using one of those feature extractions. Classification methods (KNN classification, Vector Quantization, and Simple Neural Network) affect the accuracy in detecting and recognizing of baby crying. KNN classification with LFCC results better accuracy than using MFCC one with the sample data is female voice. Ifusing baby voice, there is no significant different accuracy in both of feature extractions.