Speech recognition system and method

The present invention relates to a speech recognition system includes a server, a data transmission interface and a voice recognition device. Speech recognition apparatus linked to the server via the data transmission interface. Voice recognition means comprises a microphone, an output component and a processing component. User information to the server via the data transmission interface processing component, the received transmission to obtain a corresponding personal dictionary file. Generates speech recognition dictionary file depends on the result of the user's historical data, as well as others related to data recently used. Processing component receives the user through the microphone of a voice signal to be recognized, and in accordance with the corresponding user voiceprint file, the file is converted to a digital signature. Search processing components based on digital signature file personal dictionary file to obtain a speech recognition result and output via the output component.