A Novel Methodology to Extract Voice Signal Features

A novel methodology to manipulate wave file and create a feature array for each wave file will be introduced, this array can be used later on to recognize the voice file. A set of experiments will be performed in order to prove the uniqueness of the calculated feature array, and that the created feature array for a certain wave file does not match any other feature array for other wave files. The proposed methodology will minimize the efforts of voice recognition by mean of minimizing the time of feature array creation and minimizing the size of the calculated array.