Simultaneous support of isolated and connected phrase command recognition in automatic speech recognition systems

• US 7,620,553 B2
• Filed: 12/20/2005
• Issued: 11/17/2009
• Est. Priority Date: 12/20/2005
• 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: Stiller, Heinz-Werner, Wang, Gang, Contolini, Matteo, Zheng, Chengyi, Chatenever, David
• Primary Examiner(s): Sked; Matthew J
• Application Number:
  US11/312,785
• Publication Number:
  US 20070150288A1
• Time in Patent Office: 1,428 Days
• Field of Search: None
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A system for operating one or more devices using speech input including a receiver for receiving a speech input, a controller in communication with the receiver, software executing on the controller for converting the speech input into computer-readable data, software executing on the controller for generating a table of active commands, the table including a portion of all valid commands of the system, software executing on the controller for identifying at least one active command represented by the data, and software executing on the controller for transmitting the active command to at least one device operable by the active command.

Claims

1. A system for operating one or more devices using speech input, comprising:

a receiver for receiving a speech input including at least one of an isolated speech input and a continuous speech input;

a controller in communication with said receiver;

software executing on said controller for converting the speech input into computer-readable data;

a command menu including a plurality of command menu levels;

software executing on said controller for generating a set of active commands, the active commands selected from at least two different levels of said command menu;

software executing on said controller for querying the set of active commands to identify one active command represented by the computer-readable data if the speech input includes isolated speech input and at least two active commands represented by the data if the speech input includes continuous speech input, each of the at least two active commands from a different command menu level; and

software executing on said controller for implementing the one or more identified active commands via one or more devices operable by the system.

2. The system according to claim 1,

wherein said system command menu includes one or more global commands.

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

software executing on said controller for identifying a global command represented by the data; and

software executing on said controller for implementing the global command.

4. The system according to claim 1, wherein the one or more devices operable by the system are medical devices.

5. The system according to claim 1, wherein the set of active commands is generated and updated dynamically during use based on a current command menu location and a depth parameter.

6. A system for operating one or more devices using speech input, comprising:

a receiver for receiving a speech input including at least one of an isolated speech input and a continuous speech input;

a controller in communication with said receiver;

software executing on said controller for converting the speech input into computer-readable data;

software executing on said controller for generating a set of active commands, the set including active commands selected from at least two different levels of a command menu, wherein the active commands are generated and updated dynamically during use based on a current command menu location and a depth parameter;

software executing on said controller for querying the set of active commands and identifying at least one active command represented by the data if the speech input includes isolated speech input and at east two active commands represented by the data if the speech input includes continuous speech input; and

software executing on said controller for sending data for implementing the one or more identified active commands to one or more devices operable by the system.

7. The system according to claim 6, wherein each of the at least two active commands are sequential commands each from a different level of the command menu.

8. The system according to claim 6, wherein the set of active commands includes at least one global command.

9. The system according to claim 8, further comprising:

software executing on said controller for identifying a global command represented by the data; and

software executing on said controller for implementing the global command.

10. The system according to claim 6, wherein the one or more devices operable by the system are medical devices.

11. The system according to claim 6, wherein the set of active commands includes at least one isolated command phrase and at least one concatenated command phrase.

12. The system according to claim 6, wherein the depth parameter is indicative of a deviation from a current menu position.

13. The system according to claim 6, wherein the depth parameter is indicative of a number of menu levels.

14. The system according to claim 6, wherein said software for identifying at least one active command parses the data into one or more potential commands.

15. The system according to claim 6, wherein said software for identifying at least one active command queries a table of command equivalents.

16. A method of controlling a device using a speech input, comprising the steps of:

determining commands associated with each device of a system from a command menu;

generating a set of active commands, wherein the set includes active commands selected from at least two different levels of the command menu;

receiving a speech input including at least one of an isolated speech input and a continuous speech input;

converting the speech input into computer-readable data;

querying the set of active commands and identifying one active command represented by the data if the speech input includes isolated speech input and at least two active commands represented by the data if the speech input includes continuous speech input; and

sending data for implementing the one or more active commands to at least one device to which the active commands pertain.

17. The method according to claim 16, wherein the step of generating the set of active commands includes determining the last active command identified.

18. The method according to claim 16, wherein the step of generating the set of active commands includes utilizing a depth parameter, the depth indicative of a number of menu levels.

19. The method according to claim 16, wherein the step of identifying at least one active command includes parsing the data into one or more potential commands.

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

displaying the identified at least one active command.

21. The method according to claim 16, wherein the step of identifying the at least one active command includes generating a prompt to a user of the system.

22. The method according to claim 16, wherein the set of active commands is generated and updated dynamically during use based on a current command menu location and a depth parameter.