A Study And Design Of Lock System Based On Speaker Recognition Technology

Speaker recognition technology belongs to biometrics recognition technologies, which is the technology of automatic identity speaker's authentication, according to obtain the feature parameter which reflecting mental and physiology in voice form. Voiceprint recognition can be used to many situation ,example for information safetysecurity and people's identity recognition. At present, the speaker recognition system are work depend on computer mostly ,so the system is very expensive and serve just for a single user.This thesis introduces the foundation acoustics knowledge of speaker recognition: the mathematic model of speech signal and the characteristic parameters of speech. And then design a set of Voiceprint lock system which worked steadily and economical for multiuser. The system is made up of a host computer and several terminal, the host computer serve for all of terminal. The host computer communicat with terminal depend on the wireless mode instead of RS485 bus ,which convenience for install.TMS5509APGE chip be equal to the terminal for High-Performance, Low-Power and economical. The usb interface is designed by mcu and maked in Software with obdev USB Driver. Asynchronous communication can be automatic confirm baud rate by code period detectation and compatible for product upgrade.The testing proves that the voiceprint lock system works well and has strong adaptability and high discrimination but low cost, and the design completely acheieves the anticipative goal and of higher in practicality and stronger competition in the market.