Using voice biometrics across virtual environments in association with an avatar's movements

• US 8,140,340 B2
• Filed: 01/18/2008
• Issued: 03/20/2012
• Est. Priority Date: 01/18/2008
• Status: Active Grant

• Current Assignee: Activision Publishing Incorporated (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Bhogal, Kulvir S., Hamilton, II, Rick A., Kanevsky, Dimitri, Pickover, Clifford A., SAND, ANNE R.
• Primary Examiner(s): Smits, Talivaldis Ivars
• Application Number:
  US12/016,823
• Publication Number:
  US 20090187405A1
• Time in Patent Office: 1,523 Days
• Field of Search: 704/273, 704/275, 715/706
• US Class Current: 704/273
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

Mechanisms are provided for utilizing a voiceprint to authorize a user to perform an operation restricted to authorized users. A voiceprint is stored in an audio attribute file and is associated with a user. Based on a comparison of this voiceprint and an utterance provided by the user, an identification of the user is accomplished. If the utterance matches the voiceprint, the user is permitted to access services or perform operations. The audio attribute file may be transmitted from one virtual environment to another based on the detected movement of the user'"'"'s avatar between virtual environments. As such, the recipient computing device may use the audio attribute file to identify the user in the new virtual environment.

Claims

1. A method, in a data processing system, for utilizing a voiceprint to authorize a user to perform an operation restricted to authorized users, comprising:

a first computing device transmitting an utterance request;

the first computing device processing a first utterance in reply to the utterance request to create a voiceprint;

a storage system storing the voiceprint in an audio attribute file;

the storage system associating the voiceprint in the audio attribute file with a user of a virtual universe provided in the data processing system;

the first computing device receiving a second utterance associated with the user; and

performing identification of the user based on the second utterance by comparing the second utterance to the voiceprint;

if the identification is successful, allowing the user to access services or authorizing the user to perform operations that are restricted to authorized users;

detecting a movement of an avatar representing the user in a first virtual environment provided by the first computing device to a second virtual environment of a second computing device, different from the first computing device; and

in response to detecting the movement of the avatar from the first virtual environment to the second virtual environment, transmitting the audio attribute file to the second computing device, wherein the audio attribute file is used by the second computing device to identify the user for accessing services or authorizing the user to perform operations that are restricted to authorized users on the second computing device.

2. The method of claim 1, further comprising creating a voiceprint in response to user settings, wherein the user settings specify at least one attribute for modifying the first utterance so that a modified first utterance is not the user'"'"'s natural voice, and wherein the voiceprint is generated based on the modified first utterance.

3. The method of claim 1, further comprising transmitting a prompt to the client application requesting an utterance to authenticate the user in response to user interactions that control an activity related to the avatar.

4. The method of claim 1, further comprising transmitting a second utterance request based on an expiration of a predetermined time period to obtain the second utterance.

5. The method of claim 1, further comprising encrypting the first utterance.

6. The method of claim 1, further comprising time-stamping the first utterance and comparing the timestamp to a current time to authenticate the user, wherein if the current time is at least a threshold amount of time different from the timestamp, then authentication of the user is unsuccessful.

7. The method of claim 1, further comprising:

receiving a first identifier with the first utterance, wherein the first identifier is an identifier unique to the user;

receiving a second identifier with the second utterance; and

comparing the first identifier and the second identifier, along with the performing of identification of the user based on the second utterance, to authenticate the user.

19. The method of claim 2, wherein the at least one attribute for modifying the first utterance is an attribute specifying a blending of the first utterance with another voice that is not the user'"'"'s voice.

20. The method of claim 7, wherein the first identifier is one of an attribute of the avatar.

8. A system for utilizing a voiceprint to authorize a user to perform an operation restricted to authorized users, comprising:

one or more processors, one or more computer-readable memories, and one or more computer-readable, tangible storage devices;

program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to provide transmissions to a client application and to provide an interactive environment having at least one avatar;

program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to send an enrollment request to the client application, to receive a reply from the client application, and to create a voice profile for the at least one avatar;

program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to receive a transmission having an utterance from the client application and to compare the utterance to the voice profile and to authenticate the at least one avatar based on the comparison and allow the at least one avatar to access services or authorize the at least one avatar to perform operations that are restricted to authorized users;

program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to detect a movement of the at least one avatar from a first virtual environment provided by a first computing device to a second virtual environment of a second computing device, different from the first computing device; and

program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to, in response to detecting the movement of the at least one avatar from the first virtual environment to the second virtual environment, transmit the audio attribute file to the second computing device for use by the second computing device to identify the user for accessing services or authorizing the user to perform operations that are restricted to authorized users on the second computing device.

9. The system of claim 8, wherein the voice biometric module and the authentication module are a remotely located from the processing module.

10. The system of claim 8, further comprising program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to provide text to speech conversion to be used when generating the voice profile.

11. The system of claim 8, further comprising program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to provide voice reconstruction to reconstruct a modified voice based on the received utterance and one or more user settings, wherein the one or more user settings specify at least one attribute for modifying the utterance so that a modified utterance is not the user'"'"'s natural voice, and wherein the modified utterance is used to compare with the voice profile.

12. The system of claim 8, further comprising program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to associate a first identifier with the voice profile, wherein the first identifier is an identifier unique to the user;

program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to receive a second identifier with the utterance; and

program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to compare the first identifier and the second identifier to authenticate the user.

13. A computer program product for utilizing a voiceprint to authorize a user to perform an operation restricted to authorized users, the computer program product comprising:

one or more computer-readable, tangible storage devices;

program instructions, stored on at least one of the one or more storage devices, to transmit an utterance request;

program instructions, stored on at least one of the one or more storage devices, to receive a reply to the utterance request;

program instructions, stored on at least one of the one or more storage devices, to process the utterance request to create a voiceprint, the voiceprint generated via a user assembly process;

program instructions, stored on at least one of the one or more storage devices, to store the voiceprint in an audio attribute file that can be acquired, imported, exported and updated;

program instructions, stored on at least one of the one or more storage devices, to associate the voiceprint with an avatar of a first virtual universe; and

program instructions, stored on at least one of the one or more storage devices, to authorize the avatar to access services or authorize the avatar to perform operations that are restricted to authorized users;

program instructions, stored on at least one of the one or more storage devices, to detect a movement of the avatar from the first virtual universe provided by a first computing device to a second virtual universe of a second computing device, different from the first computing device; and

program instructions, stored on at least one of the one or more storage devices, to in response to detecting the movement of the avatar from the first virtual universe to the second virtual universe, transmit the audio attribute file to the second computing device for use by the second computing device to identify the avatar for accessing services or authorizing the avatar to perform operations that are restricted to authorized avatars on the second computing device.

14. The computer program product of claim 13, further comprising program instructions, stored on at least one of the one or more storage devices, to transmit a prompt to the client application and request an utterance to authenticate the participant when the avatar moves to a new medium.

15. The computer program product of claim 13, further comprising program instructions, stored on at least one of the one or more storage devices, to prompt the client application for an utterance to authenticate the participant based on a predetermined time period, to receive an utterance associated with the avatar, and to identify the avatar based on the received utterance.

16. The computer program product of claim 13, further comprising program instructions, stored on at least one of the one or more storage devices, to encrypt the utterance.

17. The computer program product of claim 13, further comprising program instructions, stored on at least one of the one or more storage devices, to time-stamp the utterance and compare the timestamp to wall clock time to authenticate the utterance.

18. The computer program product of claim 13, further comprising program instructions, stored on at least one of the one or more storage devices, to attach an identifier to an utterance transmission to authenticate the utterance.