Design And Implementation Of A Small-sized Voice Identity Recognition System Based On TMS320C6713

Speaker recognition is a biometrics that the identifier of a person can be recognized via his voice. It is applied to man-machine interface, ensure public security, military affairs, judicature, and so on. The identity recognition based on human voice is one of the most important ways of identity recognition. The speaker recognition technology is the processing of automatically recognition whether the speaker in the speakers whose voice records has been gathered, then determine who the speaker is, by analyzing the speaker's pronunciation signals and picking up the speaker's characteristic.This topic adopted many arithmetic, such as double-threshold endpoint detection, Mel Frequency Cepstrum Coefficient and Vector Quantization. And this paper constructed an identity recognition system based on DSP, with close small words and should be text-related. The system has several chacteristics such as the cost is cheap, stable credibility, circulate exactitude, can attain to a higher identify rate, and has stronger practical value.