Voice authentication system and method using a removable voice ID card
A voice authentication system using a removable voice ID card comprises: at server side, a voiceprint database for storing the voiceprints of all authorized users; a voiceprint updating means for updating the voiceprints in said voiceprint database; and a voiceprint digest generator for generating a voiceprint digest according to a request from a client; at client side, a voice ID card for storing the voiceprint of an authorized user; a validation means for validating the voiceprint in the voice ID card on the basis of the voiceprint digest from the server; an audio device for performing voice interaction with a user; and a voice authentication means for determining whether the voiceprint from said voice ID card is of the same speaker as the voice from said audio device.
1. A voice authentication method using a removable voice ID card, comprising the following steps:
a user inserting the voice ID card storing a voiceprint of the authorized user into a client;
the client requesting from a server a voiceprint digest corresponding to the voiceprint in the voice ID card;
the client generating a second digest of the voiceprint in the voice ID card;
comparing said two voiceprint digests;
performing a voice authentication process in case of the two digests matching and in response to determining that the two digests match, generating a text script as a pass code, and in response thereto, receiving a voice inputted by the user;
generating a semantic meaning of the voice inputted by the user; and
judging whether the semantic meaning is the same as the text script generated by said random pass code generator, thereby determining whether said user can be authorized.
2. A voice authentication system using a removable voice ID card, comprising:
a voice ID card for storing a voiceprint in a client of an authorized user;
an audio device for performing voice interaction with a user;
the client requesting from a server a first digest corresponding to the voiceprint in the voice ID card;
the client generating a second digest of the voiceprint in the voice ID card;
a voice authentication means for determining whether the voiceprint from said voice ID card is of a same speaker as voice from said audio device, in response to determining that the two digests match;
a random pass code generator for randomly generating a text script as a pass code;
a text-to-speech converting means for generating audio data according to the text script and sending it to said audio device; and
a voice recognition means for recognizing a semantic meaning of the voice inputted by the user through said audio device, and judging whether it is the same as the text script generated by said random pass code generator, thereby determining whether said user can be authorized.