Research And Implementation Of Speaker Recognition System Based On VQ And HMM

As one of the biometrics techniques, speaker recognition is the process of automatically recognizing who is speaking on the basis of individual information included in speech waves. Because of its particularly advantage on convenience,economy and extensibility, this technique can be applied to a number of areas, such as banking by telephone, telephone shopping, database access services, security control for confidential information and remote access to computers. Because of that, it is pay attention to by the researcher more and more in the biometrics techniques realm in recent years. By analyzing the general principles and system structure of speaker recognition and considerating subsistent technology of speaker recognition, linear prediction cepstrum coefficient (LPCC) and Mel cepstrum coefficient (MFCC) characteristic parameter, the vector quantization (VQ) and Hidden Markov's model (HMM) are applied to the discernment method that the speaker recognition, set up speaker's recognition system.This text introduced the concept of speaker recognition system firstly, then analyzed a few extraction methods of speech feature parameters in common use and a few models of speaker recognition. It studied Vector Quantization (VQ) and Hidden Markov Models (HMM) be used for text-dependent speaker recognition, and accomplished elementary speaker recognition system with matlab6.5. During the experiments, we use separately the VQ models of different codebook numbers and the HMM models of different Gauss mixtures for 16 people's voice samples to compare the recognition rates between them.When take the experiment's codebook number and Gauss mixture number with separately 8 or 16, the comparative trial result discovered that ,when the codebook number and Gauss mixture number are same , the hidden Markov model (HMM) compares the vector quantization model (VQ) for the language materials to have higher recognition rate.