Except for the speech text (words), the rich dimensions also refer as the gender, attitude, emotion, health situation and identity of a speaker. Such information is very important for an effective communication.
The speaker recognition systems are developed in two phases: training phase and recognition phase. In the training phase, each registered speaker has to provide samples of their speech so that the system can build a reference model for that speaker. In the testing phase, the input speech is matched with stored reference model(s) and a recognition decision is made.
One of the important decisions in any pattern recognition system is the choice of what features can be used and how exactly to represent the signal that is to be classified. Through more than many years of research, many different feature extraction techniques of the speech signal have been suggested and tried like MFCC, LPC etc. PLP is one such technique. Moreover for speaker modelling, different modelling techniques for speaker recognition system have been identified such as Gaussian Mixture Model (GMM) and Hidden Markov Model (HMM), which are prevalent techniques in this