Voice Recognition Based on Vector Quantization Using LBG

The process which recognizes the speaker based on the information present in the speech is called Voice recognition. This can be used to many applications like identification, voice dialling, tele-shopping, voice based access services, information services, tele-banking, security control of confidential information. The variation of Speaker exists in speech signals because of different resonances of the vocal tract. MFCC is the technique to exploit the differences of the speech signal. Similarly, the technique of Vector Quantization (VQ) emerged as useful tool. In this chapter, the VQ is employed for efficient creating the extracted feature vector. The acoustic vectors extracted from input speech of a speaker and provide a set of training vectors. LBG algorithm is used for clustering a set of L training vectors into a set of M codebook vectors.