System and method for voice authentication over a computer network
View Patent ↗Systems, computer-implemented methods, and tangible computer-readable media are provided for voice authentication. The method includes receiving a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource, performing a comparison of the received speech sample to a previously established speech profile associated with the user, transmitting an authentication to the network client if the comparison is equal to or greater than a certainty threshold, and transmitting a denial to the network client if the comparison is less than the certainty threshold.
1. A computer-implemented method of voice authentication, the method comprising:
receiving, via a processor of a network client, a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource;
preauthenticating the speech sample at the network client running the Internet browser;
performing a comparison of the received speech sample to a previously established speech profile associated with the user;
transmitting an authentication to the network client if the comparison is equal to or greater than a certainty threshold; and
transmitting a denial to the network client if the comparison is less than the certainty threshold.
2. The computer-implemented method of claim 1 , wherein the user captures and sends the speech sample with a single user input.
3. The computer-implemented method of claim 1 , wherein the network client running the Internet browser preauthenticates the received speech sample before sending the speech sample to a server.
4. The computer-implemented method of claim 3 , wherein the preauthentication performed at the network client is more relaxed than the authentication performed at the server.
5. The computer-implemented method of claim 1 , wherein a decision to preauthenticate is based on network conditions.
6. The computer-implemented method of claim 1 , further comprising receiving a user token and transmitting the authentication to the network client when the user token matches a previously established user token.
7. The computer-implemented method of claim 1 , the method further comprising:
sending to the user a prompt for an additional speech sample due to feigned poor speech recognition if the comparison is less than the certainty threshold;
receiving the additional speech sample from the user;
performing a second comparison of the additional received speech sample to the previously established speech profile associated with the user; and
transmitting the authentication to the network client if the second comparison is equal to or greater than a certainty threshold.
8. The computer-implemented method of claim 1 , wherein the received speech sample is a password.
9. The computer-implemented method of claim 1 , wherein the user reads specified text to generate the speech sample.
10. A system for voice authentication, the system comprising:
a module configured to receive, via a processor of a network client, a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource;
a module configured to preauthenticate the speech sample at the network client running the Internet browser;
a module configured to perform a comparison of the received speech sample to a previously established speech profile associated with the user;
a module configured to transmit an authentication to the network client if the comparison is equal to or greater than a certainty threshold; and
a module configured to transmit a denial to the network client if the comparison is less than the certainty threshold.
11. The system of claim 10 , wherein the user captures and sends the speech sample with a single user input.
12. The system of claim 10 , wherein the network client running the Internet browser preauthenticates the received speech sample before sending the speech sample to a server.
13. The system of claim 10 , further comprising a module configured to receive a user token and transmitting the authentication to the network client when the user token matches a previously established user token.
14. The system of claim 10 , the system further comprising:
a module configured to send to the user a prompt for an additional speech sample due to feigned poor speech recognition if the comparison is less than the certainty threshold;
a module configured to receive the additional speech sample from the user;
a module configured to perform a second comparison of the additional received speech sample to the previously established speech profile associated with the user; and
a module configured to transmit the authentication to the network client if the second comparison is equal to or greater than a certainty threshold.
15. A tangible non-transitory computer-readable medium storing a computer program, which upon execution on a processor, causes the processor to perform steps for voice authentication, the steps comprising:
receiving, via the processor of a network client, a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource;
preauthenticating the speech sample at the network client running the Internet browser;
performing a comparison of the received speech sample to a previously established speech profile associated with the user;
transmitting an authentication to the network client if the comparison is equal to or greater than a certainty threshold; and
transmitting a denial to the network client if the comparison is less than the certainty threshold.
16. The tangible computer-readable medium of claim 15 , wherein the user captures and sends the speech sample with a single user input.
17. The tangible computer-readable medium of claim 15 , wherein the network client running the Internet browser preauthenticates the received speech sample before sending the speech sample to a server.
18. The tangible computer-readable medium of claim 17 , wherein the preauthentication performed at the network client is more relaxed than the authentication performed at the server.
19. The tangible computer-readable medium of claim 15 , wherein a decision to preauthenticate is based on network conditions.
20. The tangible computer-readable medium of claim 15 , the method further comprising:
sending to the user a prompt for an additional speech sample due to feigned poor speech recognition if the comparison is less than the certainty threshold;
receiving the additional speech sample from the user;
performing a second comparison of the additional received speech sample to the previously established speech profile associated with the user; and
transmitting the authentication to the network client if the second comparison is equal to or greater than a certainty threshold.