Verifying a user using speaker verification and a multimodal web-based interface
View Patent ↗A method of verifying a user identity using a Web-based multimodal interface can include sending, to a remote computing device, a multimodal markup language document that, when rendered by the remote computing device, queries a user for a user identifier and causes audio of the user's voice to be sent to a multimodal, Web-based application. The user identifier and the audio can be received at about a same time from the client device. The audio can be compared with a voice print associated with the user identifier. The user at the remote computing device can be selectively granted access to the system according to a result obtained from the comparing step.
1. A method for user authentication, the method comprising acts of:
receiving from a user a request for access to content;
prior to accessing stored information associated with any of one or more users having access to the content for which access is requested:
accessing a second utterance that users are prompted to speak during an enrollment process; and
randomly selecting at least one portion of the second utterance as a first utterance with which to prompt the user;
in response to the request, sending, via a single data communication network connection to a remote computing device, information for use in authenticating the user, the information comprising a single page including both an input field for receiving a user identifier and a first prompt to be rendered to the user to prompt the user to provide a voice sample, wherein the first prompt to be rendered to the user prompts the user to speak the first utterance;
receiving, via the single data communication network connection, from the remote computing device, as a result of the remote computing device executing the single page including both the input field and the first prompt to be rendered to the user, a user identifier entered by the user into the input field and audio data representing speech spoken by the user in response to the first prompt; and
in response to receiving the user identifier and the audio data:
accessing a voice print associated with the received user identifier;
analyzing the received audio data to determine whether the received audio data matches the accessed voice print; and
selectively granting to the user access to the content based on whether the received audio data matches the accessed voice print.
2. The method of claim 1 , wherein the method further comprises an act of, during the enrollment process, sending to the user a second prompt to prompt the user to speak the second utterance.
3. The method of claim 2 , wherein the audio data is first audio data, and wherein the method further comprises acts of:
using second audio data to generate the voice print, the second audio data being provided by the user in response to the second prompt; and
storing the voice print in association with the user identifier.
4. The method of claim 1 , wherein the first prompt comprises a textual prompt instructing the user to read a displayed script.
5. The method of claim 1 , wherein the first prompt comprises a speech prompt instructing the user to speak the first utterance.
6. The method of claim 1 , wherein the page comprises a multimodal markup language document to be rendered by the remote computing device to prompt the user to enter a user identifier into the first field and to provide a voice sample.
7. At least one computer-readable storage device having stored thereon instructions that, when executed by at least one processor, perform a method for user authentication, the method comprising acts of:
receiving from a user a request for access to content;
prior to accessing stored information associated with any of one or more users having access to the content for which access is requested:
accessing a second utterance that users are prompted to speak during an enrollment process; and
randomly selecting at least one portion of the second utterance as a first utterance with which to prompt the user;
in response to the request, sending, via a single data communication network connection to a remote computing device, information for use in authenticating the user, the information comprising a single page including both an input field for receiving a user identifier and a first prompt to be rendered to the user to prompt the user to provide a voice sample, wherein the first prompt to be rendered to the user prompts the user to speak the first utterance;
receiving, via the single data communication network connection, from the remote computing device, as a result of the remote computing device processing the single page including both the input field and the first prompt to be rendered to the user, a user identifier entered by the user into the input field and audio data representing speech spoken by the user in response to the first prompt; and
in response to receiving the user identifier and the audio data:
accessing a voice print associated with the received user identifier;
analyzing the received audio data to determine whether the received audio data matches the accessed voice print; and
selectively granting to the user access to the content based on whether the received audio data matches the accessed voice print.
8. The at least one computer-readable storage device of claim 7 , wherein the method further comprises an act of, during the enrollment process, sending to the user a second prompt to prompt the user to speak the second utterance.
9. The at least one computer-readable storage device of claim 8 , wherein the audio data is first audio data, and wherein the method further comprises acts of:
using second audio data to generate the voice print, the second audio data being provided by the user in response to the second prompt; and
storing the voice print in association with the user identifier.
10. The at least one computer-readable storage device of claim 8 , wherein the page comprises a multimodal markup language document to be rendered by the remote computing device to prompt the user to enter a user identifier into the first field and to provide a voice sample.
11. The at least one computer-readable storage device of claim 7 , wherein the first prompt comprises a textual prompt instructing the user to read a displayed script.
12. The at least one computer-readable storage device of claim 7 , wherein the first prompt comprises a speech prompt instructing the user to speak the first utterance.
13. A system comprising at least one processor programmed to perform a method for user authentication, the at least one processor programmed to:
receive from a user a request for access to content;
prior to accessing stored information associated with any of one or more users having access to the content for which access is requested:
access a second utterance that users are prompted to speak during an enrollment process; and
randomly select at least one portion of the second utterance as a first utterance with which to prompt the user;
in response to the request, send, via a single data communication network connection to a remote computing device, information for use in authenticating the user, the information comprising a single markup language document including both an input field for receiving a user identifier and a first prompt to be rendered to the user to prompt the user to provide a voice sample, wherein the first prompt to be rendered to the user prompts the user to speak the first utterance;
receive, via the single data communication network connection, from the remote computing device, as a result of the remote computing device rendering the single markup language document including both the input field and the first prompt, a user identifier entered by the user into the input field and audio data representing speech spoken by the user in response to the first prompt; and
in response to receiving the user identifier and the audio data:
access a voice print associated with the received user identifier;
analyze the received audio data to determine whether the received audio data matches the accessed voice print; and
selectively grant to the user access to the content based on whether the received audio data matches the accessed voice print.
14. The system of claim 13 , wherein the at least one processor is further programmed to, during the enrollment process, send to the user a second prompt to prompt the user to speak the second utterance.
15. The system of claim 14 , wherein the audio data is first audio data, and wherein the at least one processor is further programmed to:
use second audio data to generate the voice print, the second audio data being provided by the user in response to the second prompt; and
store the voice print in association with the user identifier.
16. The system of claim 13 , wherein the first prompt comprises a textual prompt instructing the user to read a displayed script.
17. The system of claim 13 , wherein the first prompt comprises a speech prompt instructing the user to speak the first utterance.
18. The system of claim 13 , wherein the page comprises a multimodal markup language document to be rendered by the remote computing device to prompt the user to enter a user identifier into the first field and to provide a voice sample.