Method and apparatus for recognizing from here to here voice command structures in a finite grammar speech recognition system

• US 6,745,165 B2
• Filed: 06/16/1999
• Issued: 06/01/2004
• Est. Priority Date: 06/16/1999
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Boyer, Linda M., Smith, Maria E., Kist, Thomas A., Lewis, James R., Ortega, Kerry A.
• Primary Examiner(s): {haeck over (S)}mits, T{overscore (a)}livaldis Ivars
• Assistant Examiner(s): Azad, Abul K.
• Application Number:
  US09/334,112
• Publication Number:
  US 20020059071A1
• Time in Patent Office: 1,812 Days
• Field of Search: 704/251, 704/275, 704/270, 704/276
• 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 2015/223 Execution procedure of a spoken command

Abstract

A method and system uses a finite state command grammar coordinated with application scripting to recognize voice command structures for performing an event from an initial location to a new location. The method involves a series of steps, including: recognizing an enabling voice command specifying the event to be performed from the initial location; determining a functional expression for the enabling voice command defined by one or more actions and objects; storing the action and object in a memory location; receiving input specifying the new location; recognizing an activating voice command for performing the event up to the new location; retrieving the stored action and object from the memory location; and performing the event from the initial location to the new location according to the retrieved action and object. Preferably, the enabling-activating command is phrased as “from here . . . to here”. The user specifies the new location with voice commands issued subsequent to the enabling command. To reduce the occurrence of unintended events, these voice commands are counted so that if they exceed a predetermined limit, the action and object content is cleared from memory.

Claims

1. In a computer system adapted for speech recognition using a finite state grammar, a method for executing voice commands to perform an event from an initial location to a new location, comprising the steps of:

providing a single voice command comprising an enabling voice command and an activating voice command;

recognizing the enabling voice command specifying an object and an action to be performed on said object from said initial location;

storing said action and object of said enabling voice command in memory for subsequent use;

receiving at least one intermediate input relocating a pointer to indicate said new location;

recognizing the activating voice command that specifies said new location, but no action or object, wherein said activating voice command activates stored portions of said previously received enabling voice command;

responsive to recognizing said activating voice command, identifying said new location;

retrieving said previously stored action and object of said enabling voice command from said memory; and

performing said event from said initial location to said new location, such that said event is determined from, at least in part, said previously stored action and object of said enabling voice command.

2. The method of claim 1, further comprising:

determining a functional expression from said enabling voice command, said functional expression being defined by said action and object.

3. The method of claim 2, further comprising the step of clearing said action and object from said memory after performing said event.

4. The method of claim 2, further comprising the steps of:

counting recognized voice commands issued following said enabling voice command; and

clearing said action and object from said memory if said counted voice commands exceed a predetermined limit.

5. The method of claim 1, further comprising the step of, after said step of storing said action and object of said enabling voice command and before said step of recognizing an activating voice command, receiving at least one additional user input which is unrelated to said event to be performed from said initial location to said new location.

6. The method of claim 1, wherein said initial location is determined by identifying a first location of a pointer, said at least one intermediate input relocates said pointer to said new location, and said new location is determined by identifying a second location of said pointer.

7. The method of claim 1, wherein said at least one intermediate input is one or more voice commands.

8. The method of claim 1, wherein said at least one intermediate input is received from a pointing device.

9. The method of claim 1, further comprising the step of receiving user input indicating the position of said initial location.

10. The method of claim 1, wherein said enabling voice command includes “

from here” and

said activating voice command is “

to here”

.

11. A computer speech recognition system using a finite state grammar and executing voice commands to perform an event from an initial location to a new location, comprising:

means for providing a single voice command comprising an enabling voice command and an activating voice command;

means for recognizing the enabling voice command specifying an object and an action to be performed on said object from said initial location;

means for storing said action and object of said enabling voice command in memory for subsequent use;

means for receiving at least one intermediate input relocating a pointer to indicate said new location;

means for recognizing the activating voice command that specifies said new location, but no action or object, wherein said activating voice command activates stored portions of said previously received enabling voice command;

means for identifying said new location responsive to recognizing said activating voice command;

means for retrieving said previously stored action and object of said enabling voice command from said memory; and

means for performing said event from said initial location to said new location, such that said event is determined from, at least in part, said previously stored action and object of said enabling voice command.

12. The system of claim 11, further comprising:

means for determining a functional expression from said enabling voice command, said functional expression being defined by said action and object.

13. The system of claim 12, further comprising means for clearing said action and object from said memory after performing said event.

14. The system of claim 12, further comprising:

means for counting recognized voice commands issued following said enabling voice command; and

means for clearing said action and object from said memory if said counted voice commands exceed a predetermined limit.

15. The system of claim 11, further comprising:

means for receiving at least one additional user input which is unrelated to said event to be performed from said initial location to said new location, said means for receiving at least one additional user input being operative after said means for storing said action and object of said enabling voice command and before said means for recognizing an activating voice command.

16. The system of claim 11, wherein said initial location is determined by identifying a first location of a pointer, said at least one intermediate input relocates said pointer to said new location, and said new location is determined by identifying a second location of said pointer.

17. The system of claim 11, wherein said at least one intermediate input is one or more voice commands.

18. The system of claim 11, wherein said at least one intermediate input is received from a pointing device.

19. The system of claim 11, further comprising means for receiving user input indicating the position of said initial location.

20. The method of claim 11, wherein said enabling voice command includes “

from here” and

said activating voice command is “

to here”

.

21. A machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

providing a single voice command comprising an enabling voice command and an activating voice command;

recognizing the enabling voice command specifying an object and an action to be performed on said object from an initial location;

storing said action and object of said enabling voice command in memory for subsequent use;

receiving at least one intermediate input relocating a pointer to indicate said new location;

recognizing the activating voice command that specifies said new location, but no action or object, wherein said activating voice command activates stored portions of said previously received enabling voice command;

responsive to recognizing said activating voice command, identifying said new location;

retrieving said previously stored action and abject of said enabling voice command from said memory; and

performing said event from said initial location to said new location, such that said event is determined from, at least in part, said previously stored action and object of said enabling voice command.

22. The machine readable storage of claim 21, further comprising the step of:

determining a functional expression from said enabling voice command, said functional expression being defined by said action and object.

23. The machine readable storage of claim 22, further comprising the step of clearing said action and object from said memory after performing said event.

24. The machine readable storage of claim 22, further comprising the steps of:

counting recognized voice commands issued following said enabling voice command; and

clearing said action and object from said memory if said counted voice commands exceed a predetermined limit.

25. The machine readable storage of claim 21, further comprising the step of, after said step of storing said action and object of said enabling voice command and before said step of recognizing an activating voice command, receiving at least one additional user input which is unrelated to said event to be performed from said initial location to said new location.

26. The machine readable storage of claim 21, wherein said initial location is determined by identifying a first location of a pointer, said at least one intermediate input relocates said pointer to said new location, and said new location is determined by identifying a second location of said pointer.

27. The machine readable storage of claim 21, wherein said at least one intermediate input is one or more voice commands.

28. The machine readable storage of claim 21, wherein said at least one intermediate input is received from a pointing device.

29. The machine readable storage of claim 21, further comprising the step of receiving user input indicating the position of said initial location.

30. The machine readable storage of claim 21, wherein said enabling voice command includes “

from here” and

said activating voice command is “

to here”

.