The Study And The Design Of Speaker Recognition System

Speaker recognition is the process of automatically recognizing who is speakingon the basis of individual information included in speech signals. It has wellapplicationprospectsinmanyfields.Before picking up the speech signal characteristic parameters, the voice signal isundergoing pretreatment. In this phase, we should find the signal's endpoint and filterthe speech silence segment in order to provide useful speech segment. We improvetraditional methodandprovethatitisbetterthanthetraditionalone.By analyzing speech characteristic parameters and the basis methods of speakerrecognition, we choose MFCC and LPCC's difference to be the speech characteristicparameters. Using DTW and VQ to recognize text-dependent speech andtext-unpendent speech, we have developed a speaker identification system in thispaper.