Characterization between child and adult voice using machine learning algorithm

Speech Feature Detection is a technique employed in speech processing in which different features of speech are used to distinguish between speech in different age groups. This paper implements a new approach for the extraction and classification of the speech features using the Mel-frequency cepstral coefficient, and Support Vector Machine. This paper presents the Mel-frequency cepstral coefficients (MFCC) for extracting the speech features of child and adult voices. Using the support vector machine, we classify the datasets in a child and an adult´s speech.