Recognition Of Voice Using Mel Cepstral Coefficient & Vector Quantization

Human Voice is characteristic for an individual. The ability to recognize the speaker by his/her voice can be a valuable biometric tool with enormous commercial as well as academic potential. Commercially, it can be utilized for ensuring secure access to any system. Academically, it can shed light on the speech processing abilities of the brain as well as speech mechanism. In fact, this feature is being used preliminarily along with other biometrics including face and finger print recognition for commercial security products. Speaker recognition is the method of automatically identify who is speaking on the basis of individual information integrated in speech waves. There are two types of speaker recognition systems basically divided into two – classification: speaker identification and speaker verification. Speaker identification determines from which of the registered speakers a given utterance comes whereas speaker verification is the process of accepting or rejecting the claimed identity of a speaker .The fundamental difference between identification & verification modes is the number of decision alternatives. In the Identification mode the number of decision alternatives is equal to the size of the population, whereas in the verification mode there are only two alternatives, accept or reject the Identification claim, regardless of the size of population. Most applications of speaker recognition are actually speaker verifications. Speaker Recognition is of two types :Text Based and Text independent. In Text based approach, the speaker is identified by the utterance of some fixed piece of text while in the text independent approach the speaker is allowed to utter any text whatsoever.