Identification apparatus and method for receiving and processing audible commands

• US 7,415,410 B2
• Filed: 12/26/2002
• Issued: 08/19/2008
• Est. Priority Date: 12/26/2002
• Status: Active Grant

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Gardner, Robert, Campbell, William, Broun, Charles
• Primary Examiner(s): Opsasnick; Michael N
• Application Number:
  US10/329,586
• Publication Number:
  US 20040128131A1
• Time in Patent Office: 2,063 Days
• Field of Search: 704/246, 704/250, 704/273, 704/275
• US Class Current: 704/246
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

An audible command can be utilized to both permit identification of the speaker and to permit subsequent actions that comprise a corresponding response to the audible command when the identity of the speaker correlates with that of a previously authorized individual. Such identification can be supplemented with other identification mechanisms. Hierarchical levels of permission can be utilized, with or without confidence level thresholds, to further protect the device against unauthorized access and/or manipulation.

Claims

1. A method comprising:

receiving an audible command from a user;

automatically processing at least portions of the audible command with respect to previously developed identification information to correlate the user with a likely identity;

automatically responding to the audible command in a predetermined way as a function, at least in part, of the likely identity, wherein the function of likely identity includes a confidence level that the user has been correctly correlated with the likely identity, and the confidence level is compared against a respective one of a plurality of predefined threshold levels respectively corresponding to each of a plurality of different audible commands.

2. The method of claim 1 wherein automatically responding to the audible command in a predetermined way comprises automatically denying the audible command when the likely identity correlates with a user that has been previously associated with corresponding denial status.

3. The method of claim 1 wherein automatically responding to the audible command in a predetermined way as a function, at least in part, of the likely identity includes automatically responding to the audible command in a predetermined way as a function, at least in part, of the likely identity and of a second identifying metric.

4. The method of claim 3 wherein automatically responding to the audible command in a predetermined way as a function, at least in part, of the likely identity and of a second identifying metric includes automatically responding to the audible command in a predetermined way as a function, at least in part, of the likely identity and of a second identifying metric comprising at least one of:

a predetermined audible expression;

a retinal pattern;

an iris pattern;

a face pattern

a lip movement pattern

a fingerprint pattern;

a handwriting sample;

a password; and

a personal identification number.

5. The method of claim 1 wherein automatically responding to the audible command in a predetermined way comprises automatically complying with the audible command when the likely identity correlates with a user that has been previously associated with corresponding permission status.

6. The method of claim 5 wherein automatically complying with the audible command when the likely identity correlates with a user that has been previously associated with corresponding permission status includes automatically complying with the audible command when the likely identity correlates with a user that has been previously associated with corresponding permission status for all potential audible commands.

7. The method of claim 5 wherein automatically complying with the audible command when the likely identity correlates with a user that has been previously associated with corresponding permission status includes automatically complying with the audible command when the likely identity correlates with a user that has been previously associated with corresponding permission status for at least the audible command.

8. The method of claim 1 wherein automatically processing at least portions of the audible command with respect to previously developed identification information includes automatically processing at least portions of the audible command with respect to previously developed identification information comprising, at least in part, biometric information extracted from previous audible samples.

9. The method of claim 8 wherein the biometric information extracted from previous audible samples comprises, at least in part, text independent biometric information.

10. The method of claim 8 wherein the biometric information extracted from previous audible samples comprises, at least in part, text dependent biometric information.

11. The method of claim 8 wherein automatically processing at least portions of the audible command with respect to previously developed identification information further includes automatically processing at least portions of the audible command with respect to previously developed identification information that includes information that pertains, at least in part, to previous user correlations for previously received audible commands.

12. The method of claim 11 wherein automatically processing at least portions of the audible command with respect to previously developed identification information that includes information that pertains, at least in part, to previous user correlations for previously received audible commands includes automatically processing at least portions of the audible command with respect to previously developed identification information that includes information that pertains, at least in part, to previous user correlations for audible commands that have been received within a predetermined period of time.

13. A method for use with a controllable platform, comprising:

providing a plurality of user-controllable parameters;

associating each of at least some of the plurality of user-controllable parameters with at least one corresponding audible command;

providing identification information that correlates at least one audible parameter with a particular user and associating that particular user with a given permission status;

receiving an audible command from a user;

automatically processing at least portions of the audible command with respect to the identification information to determine whether the user likely comprises the particular user;

when the user likely comprises the particular user, based at least in part on a confidence level that the user is the particular user, and that the confidence level exceeds a corresponding one of a plurality of thresholds associated with the audible command, automatically responding to the audible command in a predetermined way as a function, at least in part, of the given permission status.

14. The method of claim 13 wherein:

providing a plurality of user-controllable parameters includes providing a plurality of hierarchically organized user-controllable parameters; and

automatically responding to the audible command in a predetermined way as a function, at least in part, of the given permission status includes automatically responding to the audible command in a predetermined way as a function, at least in part, of the given permission status and of at least one automatic response to at least one previously received audible command.

15. The method of claim 14 wherein automatically responding to the audible command in a predetermined way as a function, at least in part, of the given permission status and of at least one automatic response to at least one previously received audible command includes automatically responding to the audible command in a predetermined way as a function, at least in part, of the given permission status and of at least one automatic response to at least one previously received audible command, which at least one previously received audible command has a predetermined hierarchical relationship with respect to the audible command.

16. The method of claim 13, wherein providing identification information includes providing biometric information.

17. The method of claim 16 wherein providing biometric information includes providing biometric information as developed from previous audibilizations of the particular user.

18. The method of claim 17 wherein providing biometric information as developed from previous audibilizations of the particular user includes providing text-independent biometric information as developed from previous audibilizations of the particular user.

19. The method of claim 17 wherein providing biometric information as developed from previous audibilizations of the particular user includes providing text-dependent biometric information as developed from previous audibilizations of the particular user.

20. An apparatus comprising:

at least one user controllable interface having a predetermined audible command associated therewith;

a speech transducer;

at least one item of identification information that correlates at least one audible parameter with a particular user;

permission status information that is correlated with the particular user;

a speech recognition engine having an input operably coupled to the speech transducer and having a recognized audible command output operably coupled to the at least one user controllable interface;

a user identifier having an input operably coupled to the speech transducer and being operably responsive to the at least one item of identification information, and having a permission output operably coupled to at least one of the speech recognition engine and the at least one user controllable interface, wherein the user identifier comprises identification means for extracting at least one item of characterizing biometric information from an audible command as received via the speech transducer and for comparing at least portions of the at least one item of characterizing biometric information with the at least one item of identifying information to determine at least a likelihood relative to a plurality of threshold levels that the audible command was uttered by the particular user;

such that the user identifier can identify a source of an audible command as being the particular user and respond by permitting the audible command to control the at least one user controllable interface.

21. The apparatus of claim 20 wherein the apparatus comprises a wireless communications device.

22. The apparatus of claim 21 wherein the wireless communications device comprises a two-way wireless communications device.

23. The apparatus of claim 20 wherein the permission status information comprises biometric information as corresponds to previous utterances of the particular user.

24. The apparatus of claim 23 wherein the biometric information comprises one of:

text-dependent biometric information; and

text-independent biometric information.