Creating a mixed-initiative grammar from directed dialog grammars

• US 8,229,745 B2
• Filed: 10/21/2005
• Issued: 07/24/2012
• Est. Priority Date: 10/21/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Ativanichayaphong, Soonthorn, Jaramillo, David, McCobb, Gerald M.
• Primary Examiner(s): Godbold, Douglas
• Assistant Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US11/163,522
• Publication Number:
  US 20070094026A1
• Time in Patent Office: 2,468 Days
• Field of Search: 704/9, 704/240, 704/251, 704/257, 704/270, 704/270.1, 704/E15.04, 704/4, 704/271, 704/275, 704/231, 704/255, 704/10
• US Class Current: 704/257
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks

Abstract

A method of building a mixed-initiative grammar can include receiving one or more conjoin phrases, wherein each conjoin phrase is associated with a selected one of the plurality of directed dialog grammars, and receiving a user input specifying a selected grammar generation technique. The mixed-initiative grammar can be automatically generated, in accordance with the selected grammar generation technique, such that the mixed-initiative grammar specifies an allowable ordering of sets when interpreting a user spoken utterance and whether duplicative phrases are allowable within the user spoken utterance.

Claims

1. A method of building a mixed-initiative grammar comprising:

responsive to receiving a user input, creating a plurality of sets, wherein each set comprises an association of at least one conjoin phrase and at least one directed dialog grammar, wherein the at least one conjoin phrase, when recognized within a user spoken utterance, indicates that the at least one directed dialog grammar associated with the at least one conjoin phrase is used when processing speech recognized text adjacent to the at least one conjoin phrase within the user spoken utterance;

prompting the user to select from among at least two grammar generation techniques, wherein the at least two grammar generation techniques are selected from a group consisting of a fixed order technique, a wide combination technique, and a narrow combination technique;

receiving a user input specifying one of the at least two grammar generation techniques; and

automatically generating the mixed-initiative grammar, wherein the mixed-initiative grammar specifies an allowable ordering of the plurality of sets corresponding to an allowable ordering of phrases within the user spoken utterance and specifies whether duplicative phrases are allowable within the user spoken utterance in accordance with the selected grammar generation technique.

4. The method of claim 1, wherein the selected grammar generation technique specifies that the plurality of sets are used in a fixed order when interpreting the user spoken utterance.

5. The method of claim 1, wherein the selected grammar generation technique specifies that the plurality of sets are used in any order when interpreting the user spoken utterance, wherein the selected grammar generation technique allows duplicative phrases.

6. The method of claim 1, wherein the selected grammar generation technique dictates that the plurality of sets are used in any order when interpreting the user spoken utterance and that duplicative phrases are ignored.

7. The method of claim 1, further comprising prompting a user by displaying a graphical user interface comprising an input area for receiving at least one user-specified prefix type of conjoin phrase that, when recognized within the user spoken utterance, indicates that the directed dialog grammar associated with the prefix type of conjoin phrase is used when processing speech recognized text immediately following the conjoin phrase.

8. The method of claim 1, further comprising prompting a user by displaying a graphical user interface comprising an input area for receiving at least one suffix type of conjoin phrase that, when recognized within the user spoken utterance, indicates that the directed dialog grammar associated with the suffix type of conjoin phrase is used when processing speech recognized text immediately preceding the conjoin phrase.

2. A method of automatically constructing a mixed-initiative grammar from a plurality of directed dialog grammars, said method comprising:

presenting a graphical user interface comprising a first section that receives a user input specifying a prefix type of conjoin phrase, a second section that receives a user input specifying a directed dialog grammar that is associated with the prefix type of conjoin phrase, and a third section that receives a user input specifying a suffix type of conjoin phrase that is associated with the directed dialog grammar;

receiving, within the graphical user interface, at least one user input associating conjoin phrases with directed dialog grammars thereby generating a plurality of sets, wherein each set comprises a prefix and/or a suffix type of conjoin phrase and a directed dialog grammar, wherein the conjoin phrase, when recognized within a user spoken utterance, indicates that the directed dialog grammar associated with the conjoin phrase is used when processing speech recognized text adjacent to the conjoin phrase within the user spoken utterance;

prompting the user to select from among at least two grammar generation techniques, wherein the at least two grammar generation techniques are selected from a group consisting of a fixed order technique, a wide combination technique, and a narrow combination technique;

receiving a user input specifying one of the at least two grammar generation techniques; and

automatically generating the mixed-initiative grammar, wherein the mixed initiative grammar specifies an allowable ordering of the plurality of sets corresponding to an allowable ordering of phrases within the user spoken utterance and specifies whether duplicative phrases are allowed within the user spoken utterance according to the selected grammar generation technique.

9. The method of claim 2, wherein the selected grammar generation technique dictates that the plurality of sets are used in a fixed order when interpreting the user spoken utterance.

10. The method of claim 2, wherein the selected grammar generation technique dictates that the plurality of sets are used in any order when interpreting the user spoken utterance, wherein the selected grammar generation technique allows duplicative phrases.

11. The method of claim 2, wherein the selected grammar generation technique dictates that the plurality of sets are used in any order when interpreting the user spoken utterance irrespective of duplicative phrases.

12. The method of claim 2, further comprising, responsive to a prompt, receiving a user input specifying an initial prompt to be played by a mixed-initiative system, wherein the initial prompt elicits a user spoken utterance that is processed using the mixed-initiative grammar created in said generating step.

3. A non-transitory computer readable medium encoded with a plurality of instructions that, when executed by a computer, performs a method comprising:

responsive to receiving a user input, creating a plurality of sets, wherein each set comprises an association of at least one conjoin phrase and at least one directed dialog grammar, wherein the at least one conjoin phrase, when recognized within a user spoken utterance, indicates that the at least one directed dialog grammar associated with the at least one conjoin phrase is to be used when processing speech recognized text adjacent to the at least one conjoin phrase within the user spoken utterance;

prompting the user to select from among at least two grammar generation techniques, wherein the at least two grammar generation techniques are selected from a group consisting of a fixed order technique, a wide combination technique, and a narrow combination technique;

receiving a user input specifying one of the at least two grammar generation techniques; and

automatically generating the mixed-initiative grammar, wherein the mixed-initiative grammar specifies an allowable ordering of sets corresponding to an allowable ordering of phrases within the user spoken utterance and specifies whether duplicative phrases are allowable within the user spoken utterance in accordance with the selected grammar generation technique.

13. The computer readable medium of claim 3, wherein the selected grammar generation technique specifies that the plurality of sets are used in a fixed order when interpreting the user spoken utterance.

14. The computer readable medium of claim 3, wherein the selected grammar generation technique specifies that the plurality of sets are used in any order when interpreting the user spoken utterance, wherein the selected grammar generation technique allows duplicative phrases.

15. The computer readable medium of claim 3, wherein the selected grammar generation technique dictates that the plurality of sets are used in any order when interpreting the user spoken utterance and that duplicative phrases are ignored.

16. The computer readable medium of claim 3, wherein prompting the user comprises displaying a graphical user interface comprising an input area for receiving at least one user-specified prefix type of conjoin phrase that, when recognized within the user spoken utterance, indicates that the directed dialog grammar associated with the prefix type of conjoin phrase is used when processing speech recognized text immediately following the conjoin phrase.

17. The computer readable medium of claim 3, wherein prompting the user comprises displaying a graphical user interface comprising an input area for receiving at least one suffix type of conjoin phrase that, when recognized within the user spoken utterance, indicates that the directed dialog grammar associated with the suffix type of conjoin phrase is used when processing speech recognized text immediately preceding the conjoin phrase.