Comparative study regarding characteristic features of the human voice

Each human voice has its own characteristic features. The features that describe the human voice can be: the pitch, the energy of the signal, the mean value, the median value, the MFCC coefficients, and others. Some of the natural questions that come to mind are: which are the features that best characterize the human voice? What is the minimum number of features that can completely characterize the human voice? In order to answer these questions a database of human voices is used, along with different feature extraction algorithms. Just extracting the features is not enough. Some classification algorithms need to be compared in order to find the best one for the data that is available.