Voice authentication system and method using a removable voice ID card

1. A voice authentication system using a removable voice ID card, comprising:

a voiceprint database of a server for storing voiceprints of all authorized users;

a voiceprint updating means of the server for updating each voiceprint of the voiceprints, wherein each voiceprint is updated in said voiceprint database;

a voiceprint digest generator of the server for generating a first voiceprint digest according to a request from a client;

a means for generating a second voiceprint digest in the voice ID card of the client;

the voice ID card for storing a voiceprint of an authorized user;

a validation means of the client for validating the voiceprint in the voice ID card on the basis of the first voiceprint digest from the server;

an audio device of the client for performing voice interaction with the authorized user; and

a voice authentication means of the client for determining whether the voiceprint from said voice ID card belongs to the authorized user after matching the first voiceprint digest with the second voiceprint digest.

2. The voice authentication system according to claim 1 , wherein, said voice authentication system, at client side, further comprises:

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 based on the text script and sending it to said audio device;

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.

3. The voice authentication system according to claim 1 wherein, said voiceprint database includes the voiceprint digests corresponding to the respective voiceprints; and said voiceprint digest generator is used to retrieve the corresponding voiceprint digest from said voiceprint database according to the request from the client.

4. The voice authentication system according to claim 1 wherein, said digest generator generates in real time the requested voiceprint digest according to the request from the client.

5. The voice authentication system according to claim 1 wherein, said voice authentication system, at client side, further comprises:

a timer for recording the period from the user being informed to input voice to the voice being inputted.

6. The voice authentication system according to claim 5 , wherein, said voice authentication system, at client side, further comprises: a counter for recording the times of failure of authentication.

7. 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 an authorized user into a client;

the client requesting from the server a first voiceprint digest corresponding to the voiceprint in the voice ID card;

the client generating a second voiceprint digest in the voice ID card;

authenticating the user by the client by comparing the first voiceprint digest with the second voiceprint digest,

wherein the user is authenticated if the first voiceprint digest matches the second voiceprint digest; and

updating the voiceprint of the authorized user in the server.

8. The voice authentication method according to claim 7 , wherein, authenticating further comprises:

the client randomly generating a pass code, converting it to voice, and playing it to the user;

the user repeating said voice;

the client recognizing a semantic meaning of the voice inputted by the user through the audio device, and

judging whether it is the same as the text script corresponding to said pass code, thereby determining whether said user can be authorized.

9. The voice authentication method according to claim 7 wherein, said voice authentication method further comprises:

starting timing at the same time of performing the step of informing the user to input voice; and

denoting that the authentication fails if the user has not input voice in a pre-determined period.

10. The voice authentication method according to claim 9 , wherein, said voice authentication method further comprises:

prompting the user to input voice once again when the authentication fails;

recording the times of failure of authentication; and

rejecting the user's request and this authentication ending when said times of failure exceeds a pre-determined value.