Speech recognition system with user profiles management component

• US 8,015,014 B2
• Filed: 06/16/2006
• Issued: 09/06/2011
• Est. Priority Date: 06/16/2006
• Status: Active Grant

• Current Assignee: Storz Endoskop Produktions GmbH (Karl Storz Se & Co. Kg)
• Original Assignee: Storz Endoskop Produktions GmbH (Karl Storz Se & Co. Kg)
• Inventors: Wang, Gang, Zheng, Chengyi, Stiller, Heinz-Werner, Contolini, Matteo
• Primary Examiner(s): Opsasnick; Michael N
• Application Number:
  US11/455,248
• Publication Number:
  US 20070294081A1
• Time in Patent Office: 1,908 Days
• Field of Search: 704/270.1, 704/275
• US Class Current: 704/275
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A speech recognition and control system continuously operable by two or more users. The system includes a receiver for receiving a speech input, a processor in communication with the receiver and a database in communication with the processor. The database includes user profiles. The system also includes profile management software executing on the processor for determining an active profile from the plurality of user profiles, and software executing on the processor for identifying at least one command from the speech input based on the active profile.

Claims

1. A speech recognition and control system continuously operable by two or more users, comprising:

a receiver for receiving a speech input;

a processor in communication with said receiver;

a database in communication with said processor, said database including a plurality of user profiles, wherein each of the plurality of user profiles includes a speech recognition profile and one or more user preferences;

profile management software executing on said processor for determining an active profile from the plurality of user profiles; and

software executing on said processor for identifying at least one command from the speech input based on the active profile;

wherein said profile management software, after receiving a profile selection indicative of a second one of the plurality of profiles, compares the active profile to the second profile to determine conflicts between the active and second profiles pertaining to any devices being controlled by the system before switching the active profile to the second one of the plurality of user profiles during runtime of the speech recognition and control system.

2. The system according to claim 1, further comprising:

software for generating a notification upon switching the active profile.

3. The system according to claim 2, wherein the software for generating a notification generates at least one of an audio notification and a visual notification.

4. The system according to claim 2, wherein the notification includes a user identifier corresponding to the active profile.

5. The system according to claim 1, wherein the profile selection is one of a spoken selection, a manual selection, and an automatic selection.

6. The system according to claim 1, wherein the profile selection includes a unique user identifier.

7. The system according to claim 1, wherein said profile management software generates an alert if a potential conflict is found.

8. The system according to claim 1, wherein the user preferences include at least one of a speech recognition profile, a display preferences profile, a device preferences profile, and a feedback preferences profile.

9. The system according to claim 1, wherein one of the plurality of user profiles is a default profile.

10. The system according to claim 1, wherein one or more of the plurality of user profiles is editable by said profile management software.

11. The system according to claim 1, further comprising:

software executing on said processor for implementing the at least one command.

12. A speech recognition and control system continuously operable by two or more users, comprising:

a receiver for receiving a speech input;

a database including a plurality of user profiles, wherein each of the plurality of user profiles includes a speech recognition profile and one or more user preferences;

a profile manager for determining an active profile from the plurality of user profiles;

a recognizer for identifying at least one potential command from the speech input based on the active profile;

a command controller for determining at least one device command from the at least one potential command and implementing the at least one device command; and

wherein said profile management software, after receiving a profile selection indicative of a second one of the plurality of profiles, compares the active profile to the second profile to determine conflicts between the active and second profiles pertaining to any devices being controlled by the system before switching the active profile to the second one of the plurality of user profiles during runtime of the speech recognition and control system.

13. The system according to claim 12,

wherein said recognizer determines the particular one of the two or more users providing the speech input based on voice recognition, and

wherein said profile manager switches the active profile to one of the plurality of user profiles corresponding to the particular user.

14. A method of recognizing and implementing spoken commands in a voice-driven device control system, comprising the steps of:

determining, via software executing on a processor, an new active profile from one of a plurality of user profiles by receiving a user selection indicative of a user profile, wherein each of the plurality of user profiles includes a speech recognition profile and one or more user preferences;

comparing, via software executing on the processor, the selected user profile to a current active profile to determine conflicts between the selected user profile and the current active profile pertaining to any devices being controlled by the system;

activating the selected user profile without restarting the voice-driven device control system;

receiving a speech input via a receiver;

recognizing, via software executing on the processor, at least one command from the speech input based on the active profile; and

implementing, via software executing on the processor, the at least one command.

15. The method according to claim 14, wherein said step of implementing the command includes transmitting the command to at least one device operable by the voice-driven device control system.

16. A method of switching users of a speech recognition and control system during runtime, comprising the steps of:

receiving a user selection indicative of a user profile;

determining, from a plurality of user profiles, the user profile corresponding to the user selection via software executing on a processor;

comparing, via software executing on the processor, the selected user profile to a current active profile to determine conflicts between the selected user profile and the current active profile pertaining to any devices being controlled by the system; and

activating, via software executing on the processor, the user profile if no conflicts exist between the selected user profile and the current active profile.

17. The method according to claim 16, further comprising the step of:

generating a notification via software executing on the processor, the notification indicative of one of a conflict and a new active profile.

18. The method according to claim 16, wherein said step of determining a user profile includes querying, via software executing on the processor, a database of a plurality of user profiles.

19. The method according to claim 16, wherein the user selection is received as one of a speech input, a manual selection, and an automatic selection.

20. The method according to claim 16, wherein the user selection includes a unique user identifier.