ZONE BASED PRESENCE DETERMINATION VIA VOICEPRINT LOCATION AWARENESS

• US 20130195285A1
• Filed: 01/30/2012
• Published: 08/01/2013
• Est. Priority Date: 01/30/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: DE LA FUENTE, STEPHANIE, JONES, GREGORY S., PANNELL, JOHN S.
• Granted Patent: US 9,401,058 B2
• Time in Patent Office: Days
• US Class Current: 381/92
• CPC Class Codes: G01S 5/18 using ultrasonic, sonic, or infrasonic waves
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: H04R 2201/405 Non-uniform arrays of transducers or a plurality of uniform arrays with different transducer spacing
• CPC Class Codes: H04R 29/005 Microphone arrays
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407

Abstract

A speech from a speaker proximate to one or more microphones within an environment can be received. The microphones can be a directional microphone or an omni-directional microphone. The speech can be processed to produce an utterance to determine the identity of the speaker. The identity of the speaker can be associated with a voiceprint. The identity can be associated with a user'"'"'s credentials of a computing system. The credentials can uniquely identify the user within the computing system. The utterance can be analyzed to establish a zone in which the speaker is present. The zone can be a bounded region within the environment. The zone can be mapped within the environment to determine a location of the speaker. The location can be a relative or an absolute location.

Claims

1. A method for voiceprint based location awareness comprising:

receiving a speech from a speaker proximate to at least one of a plurality of microphones within an environment;

processing the speech to produce an utterance to determine the identity of the speaker, wherein the identity of the speaker is associated with a voiceprint, wherein the identity is associated with a user credentials of a computing system, wherein the user credentials uniquely identifies the user within the computing system;

analyzing the utterance to establish a zone in which the speaker is present, wherein the zone is a bounded region within the environment; and

mapping the zone within the environment to determine a location of the speaker.

2. The method of claim 1, wherein the plurality of microphones is at least one of a directional microphone and an omni-directional microphone, wherein the speaker is a person authorized to access the computing system, wherein the computing system is owned by an entity that employs the person, wherein the location is at least one of a relative and absolute location.

3. The method of claim 1, wherein the analyzing comprises of at least one triangulation computation that determines a user location based in part upon acoustic echoes unique to the bounded region resulting from the speech or from ambient noise in the environment.

4. The method of claim 1, further comprising:

identifying a voiceprint database, wherein the voiceprint database comprises of at least one voiceprint associated with a speaker; and

matching the utterance of the speaker to a voiceprint within the voiceprint database.

5. The method of claim 4, wherein the matching fails to match an utterance of the speaker to a voiceprint within the voiceprint database, establishing the speaker identity as a guest to the zone, wherein a plurality of people authorized to be in the zone by an entity owning or leasing the bounded region each have user-specific voiceprints stored.

6. The method of claim 1, further comprising:

receiving a voiceprint from a computing device associated with the speaker identity, wherein the speaker identity is associated with a user of the computing system;

storing the voiceprint and a speaker identity within a voiceprint database;

subsequently determining the identity of the speaker based on a speech utterance associated with the user, wherein the determining matches the identity of a speaker to a voiceprint within the voiceprint database; and

establishing the location of the speaker via the speech utterance.

7. The method of claim 1, further comprising:

continuously tracking a plurality of locations associated with the speaker within the environment based on subsequent utterances, wherein the plurality of locations is a plurality of zones within the environment.

8. The method of claim 7, further comprising:

evaluating the plurality of locations associated with the speaker; and

forecasting a subsequent location associated with the speaker based on the evaluating.

9. The method of claim 1, wherein the zone is at least one of a room, a building, and a geographically bounded region.

10. The method of claim 1, confirming the geographic region using a GPS equipped device, wherein mapping of the zone for the speaker based on the voice print is used to supplement presence data for enclosed environments where GPS signals are unreliable due to radio frequency interference.

11. A system for voiceprint based location awareness comprising:

a speech engine configured to determine the location of a speaker within an environment based on a received speech utterance, wherein the utterance is received from a plurality of microphones proximate to the speaker, wherein the location is at least one of a plurality of zones within the environment, wherein the utterance is matched to a voiceprint, wherein the voiceprint is associated to a speaker identity; and

a data store able to persist at least one voiceprint associated with a speaker identity and a mapping, wherein the speaker identity is associated with a user credential of a computing system, wherein the mapping associates at least one of the plurality of zones with the environment.

12. The system of claim 11, further comprising:

an utterance processor able to determine an utterance associated with a speaker within the environment;

a verification engine configured to establish the identity of the speaker based on the utterance, wherein the identity of the speaker is associated with a voiceprint, wherein the voiceprint is matched against the utterance; and

a locator capable of identifying a zone within the environment in which the speaker is present.

13. The system of claim 11, wherein each of the plurality of microphones is associated with each of the plurality of zones within the environment, wherein the plurality of microphones is at least one of a direction and an omni-directional microphone.

14. The system of claim 11, wherein at least one of the plurality of zones is at least one of a room, a building, and a geographically bounded region.

15. The system of claim 11, wherein the location is at least one of a Global Positioning System (GPS) location and a location associated with a Cartesian coordinate system.

16. The system of claim 11, wherein the locator is configured to forecast the location of the speaker based on a plurality of criteria, wherein the plurality of criteria is at least one of a date, a time, and a plurality of historic locations.

17. The system of claim 11, further comprising:

an authentication component able to permit or deny access to a resource responsive to determining the location of the speaker, wherein the component is associated with an access control system, wherein the access control system is associated with the environment.

18. The system of claim 11, wherein the speech engine is configured to automatically generate a voiceprint of a speaker from an utterance, wherein the speech engine is able to match the voiceprint to a speaker identity, wherein the speaker identity is associated with a user credentials associated with a computing system.

19. The system of claim 11, wherein the speech engine fails to match the voiceprint with an existing user identity, programmatically assigning a temporary user identity to the voiceprint.

20. A computer program product comprising a computer readable storage medium having computer usable program code embodied therewith, the computer usable program code comprising:

computer usable program code stored in a storage medium, if said computer usable program code is run by a processor it is operable to receive a speech from a speaker proximate to at least one of a plurality of microphones within an environment, wherein the plurality of microphones is at least one of a directional microphone and an omni-directional microphone, wherein the speaker is a personnel;

computer usable program code stored in a storage medium, if said computer usable program code is run by a processor it is operable to process the speech to produce an utterance to determine the identity of the speaker, wherein the identity of the speaker is associated with a voiceprint, wherein the identity is associated with a user credentials of a computing system, wherein the user credentials uniquely identifies the user within the computing system;

computer usable program code stored in a storage medium, if said computer usable program code is run by a processor it is operable to analyze the utterance to establish a zone in which the speaker is present, wherein the zone is a bounded region within the environment; and

computer usable program code stored in a storage medium, if said computer usable program code is run by a processor it is operable to map the zone within the environment to determine a location of the speaker, wherein the location is at least one of a relative and absolute location.

21. The computer program product of claim 20, further comprising:

computer usable program code stored in a storage medium, if said computer usable program code is run by a processor it is operable to receive a voiceprint from a computing device associated with the speaker identity, wherein the speaker identity is associated with a user of the computing system;

computer usable program code stored in a storage medium, if said computer usable program code is run by a processor it is operable to store the voiceprint and a speaker identity within a voiceprint database;

computer usable program code stored in a storage medium, if said computer usable program code is run by a processor it is operable to subsequently determine the identity of the speaker based on a speech utterance associated with the user, wherein the determining matches the identity of a speaker to a voiceprint within the voiceprint database; and

computer usable program code stored in a storage medium, if said computer usable program code is run by a processor it is operable to establish the location of the speaker via the speech utterance.

22. A computer system 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 processing by at least one of the one or more processors via at least one of the one or more memories, to receive a speech from a speaker proximate to at least one of a plurality of microphones within an environment;

program instructions, stored on at least one of the one or more storage devices for processing by at least one of the one or more processors via at least one of the one or more memories, to process the speech to produce an utterance to determine the identity of the speaker, wherein the identity of the speaker is associated with a voiceprint, wherein the identity is associated with a user credentials of a computing system, wherein the user credentials uniquely identifies the user within the computing system;

program instructions, stored on at least one of the one or more storage devices for processing by at least one of the one or more processors via at least one of the one or more memories, to analyze the utterance to establish a zone in which the speaker is present, wherein the zone is a bounded region within the environment; and

program instructions, stored on at least one of the one or more storage devices for processing by at least one of the one or more processors via at least one of the one or more memories, to map the zone within the environment to determine a location of the speaker.

23. The system of claim 22, wherein the microphones in the environment are stationary microphones not associated with a mobile device able to be carried by the speaker.

24. The system of claim 22, further comprising:

a speech engine of a speech processing system configured to determine the location of a speaker within the environment; and

a data store for persisting at least one voiceprint used to determine the identity of the speaker.

25. A 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 receive a speech from a speaker proximate to at least one of a plurality of microphones within an environment;

program instructions, stored on at least one of the one or more storage devices, to process the speech to produce an utterance to determine the identity of the speaker, wherein the identity of the speaker is associated with a voiceprint, wherein the identity is associated with a user credentials of a computing system, wherein the user credentials uniquely identifies the user within the computing system, wherein the identity is determined by;

I) identifying a voiceprint database, wherein the voiceprint database comprises of at least one voiceprint associated with a speaker;

II) matching the utterance of the speaker to a voiceprint within the voiceprint database, wherein the matching fails to match an utterance of the speaker to a voiceprint within the voiceprint database, establishing the speaker identity as a guest to the zone;

program instructions, stored on at least one of the one or more storage devices, to analyze the utterance to establish a zone in which the speaker is present, wherein the zone is a bounded region within the environment; and

program instructions, stored on at least one of the one or more storage devices, to map the zone within the environment to determine a location of the speaker.