The Research On Speaker Recognition Of Wireless Access Control System

Speaker recognition is a kind of biological certification technology. In the biological certification area,speaker recognition widely draws the attention because of its convenience,efficiency and accuracy. At present ,the speaker recognition system are work depend on computer mostly,so the system is expensive and serve just for a single user. To a certain extent, it hindered the speaker recognition access control system developmentThis article review the courses of speech recognition technology. On the basis of the above,the basic theory of speaker recognition is introduced according to the model of speaker recognition system,which includes the voice signals'pretreatment and the detection of endpoint.Comparing the traditional method of detection,this paper proposes a double threshold comparative method.The feature is extracted and it is focus on the inverted pedigree of LPC and Mel scale frequency.The speaker recognition algorithm DTW is introduced and analyzed in the paper. Each part of the algorithm is verified on the MATLAB simulation.In the hardware design, the system uses the digital signal processor of TMS320VC5509A as the core, high-fidelity voice codec chip TLV320AIC23, synchronous dynamic random access memory SDRAM and asynchronous memory FLASH as the main peripherals. The part of hardware circuit design specifically includes power modules, clock modules, external expansion memory modules, audio codec modules, JTAG interface and Si4432 mode . Based on CCS development environment, this piece of paper has parallel EMIF-boot mode to achieve the on-chip bootloader of the digital signal processor of TMS320VC5509A after online simulation. Using modular programming methods, procedures using C language and assembly language hybrids programming.It finished the speech recognition engineering and wireless data transceiver engineering. It is proved that the design scheme of the system is effective.