Assigning meanings to utterances in a speech recognition system

• US 7,127,394 B2
• Filed: 02/18/2004
• Issued: 10/24/2006
• Est. Priority Date: 12/31/1992
• Status: Expired due to Fees

• Current Assignee: Apple Inc.
• Original Assignee: Apple Computer Incorporated (Apple Inc.)
• Inventors: Strong, Robert Don
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US10/781,998
• Publication Number:
  US 20040162729A1
• Time in Patent Office: 979 Days
• Field of Search: None
• US Class Current: 704/255
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Assigning meanings to spoken utterances in a speech recognition system. A plurality of speech rules is generated, each of the of speech rules comprising a language model and an expression associated with the language model. At one interval (e.g. upon the detection of speech in the system), a current language model is generated from each language model in the speech rules for use by a recognizer. When a sequence of words is received from the recognizer, a set of speech rules which match the sequence of words received from the recognizer is determined. Each expression associated with the language model in each of the set of speech rules is evaluated, and actions are performed in the system according to the expressions associated with each language model in the set of speech rules.

Claims

1. A computer implemented method comprising:

determining a set of speech rules which match a spoken sequence of words by searching a current language model, said spoken sequence of words received through an audio input, said current language model generated from a plurality of speech rules according to a current operating context, wherein each of said plurality of speech rules comprises a language model and an expression; and

evaluating said expressions in said current language model to assign a meaning to said spoken sequence of words.

2. The computer implemented method of claim 1 wherein each said expression comprises an arithmetic calculation for data that varies with operating context.

3. The computer implemented method of claim 1 wherein each said language model in each of said plurality of speech rules comprises recursive references to other language models.

4. The computer implemented method of claim 3 wherein each of said language models comprise expressions associated with each of said other language models.

5. The computer implemented method of claim 4 wherein said evaluation comprises evaluating each of said expressions for said other language models prior to evaluating each said language model in each speech rule of said set of speech rules.

6. The computer implemented method of claim 1 further comprising:

generating said plurality of speech rules.

7. The computer implemented method of claim 1 further comprising:

determining said current operating context; and

generating said current language model.

8. The computer implemented method of claim 7, wherein determining said current operating context comprises determining a context for each executing application and a state for an operating system.

9. The computer implemented method of claim 1, wherein said plurality of speech rules comprises dynamic category speech rules and command speech rules, wherein each dynamic category speech rule comprises an expression that is evaluated to generate a current language model and each command speech rule comprises an expression that is evaluated to assign a meaning to a spoken sequence of words.

10. An apparatus for associating meanings to utterances in a speech recognition system comprising:

means for determining a set of said speech rules which match a spoken sequence of words by searching a current language model, said spoken sequence of words received through an audio input, said current language model generated from a plurality of speech rules according to a current operating context, wherein each of said plurality of speech rules comprises a language model and an expression; and

means for evaluating said expressions in said current language model to determine a meaning for said spoken sequence of words.

11. A computer-readable storage medium having executable instructions that cause a processor to perform a method comprising:

determining a set of speech rules that match a spoken sequence of words by searching a current language model, said spoken sequence of words received through an audio input, said current language model generated from a plurality of speech rules according to a current operating context, wherein each of said plurality of speech rules comprises a language model and an expression; and

evaluating said expressions in said current language model to assign a meaning to said spoken sequence of words.

12. The computer-readable storage medium of claim 11 wherein each said expression comprises an arithmetic calculation for data that varies with operating context.

13. The computer-readable storage medium of claim 11 wherein each said language model in each of said plurality of speech rules comprises recursive references to other language models.

14. The computer-readable storage medium of claim 13 wherein each of said language models comprise expressions associated with each of said other language models.

15. The computer-readable storage medium of claim 14 wherein said evaluation comprises evaluating each of said expressions for said other language models prior to evaluating each said language model in each speech rule of said set of speech rules.

16. The computer-readable storage medium of claim 11 further comprising:

determining said current operating context; and

generating said current language model.

17. The computer-readable medium of claim 16, wherein determining said current operating context comprises determining a context for each executing application and a state for an operating system.

18. The computer-readable medium of claim 11, wherein said plurality of speech rules comprises dynamic category speech rules and command speech rules, wherein each dynamic category speech rule comprises an expression that is evaluated to generate a current language model and each command speech rule comprises an expression that is evaluated to assign a meaning to a spoken sequence of words.

19. The computer-readable medium of claim 11 further comprising:

generating said plurality of speech rules.

20. A computer implemented method comprising:

determining a current operating context; and

generating a current language model from a plurality of speech rules according to said current operating context to define a vocabulary for a spoken sequence of words received through an audio input, wherein each of said plurality of speech rules comprises a language model and an expression.

21. The computer implemented method of claim 20, wherein determining said current operating context comprises determining a context for each executing application and a state for an operating system.

22. The computer implemented method of claim 20, wherein said plurality of speech rules comprises dynamic category speech rules and command speech rules, wherein each dynamic category speech rule comprises an expression that is evaluated to generate a current language model and each command speech rule comprises an expression that is evaluated to interpret a spoken sequence of words.

23. The computer implemented method of claim 20 further comprising:

transmitting said current language model to a speech recognition process.

24. An apparatus comprising:

means for determining a current operating context; and

means for generating a current language model from a plurality of speech rules according to said current operating context to define a vocabulary for a spoken sequence of words received through an audio input, wherein each of said plurality of speech rules comprises a language model and an expression.

25. A computer-readable storage medium having executable instructions that cause a processor to perform a method comprising:

determining a current operating context; and

generating a current language model from a plurality of speech rules according to said current operating context to define a vocabulary for a spoken sequence of words received through an audio input, wherein each of said plurality of speech rules comprises a language model and an expression.

26. The computer-readable storage medium of claim 25, wherein determining said current operating context comprises determining a context for each executing application and a state for an operating system.

27. The computer-readable storage medium of claim 25, wherein said plurality of speech rules comprises dynamic category speech rules and command speech rules, wherein each dynamic category speech rule comprises an expression that is evaluated to generate a current language model and each command speech rule comprises an expression that is evaluated to interpret a spoken sequence of words.

28. The computer-readable storage medium of claim 25 further comprising:

transmitting said current language model to a speech recognition process.

29. A computer system comprising:

a processor coupled to a computer-readable storage medium having executable instructions that cause said processor to perform a method comprising;

determining a current operating context; and

generating a current language model from a plurality of language rules according to said current operating context to define a vocabulary for a spoken sequence of words received through an audio input, wherein each of said plurality of language rules comprises a language model and an expression.