Modifying a grammar of a hierarchical multimodal menu in dependence upon speech command frequency

• US 8,090,584 B2
• Filed: 06/16/2005
• Issued: 01/03/2012
• Est. Priority Date: 06/16/2005
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Cross, Charles W. Jr., Hollinger, Michael C., Jablokov, Igor R., Lewis, Benjamin D., Pike, Hilary A., Smith, Daniel M., Wintermute, David W., Zaitzeff, Michael A.
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US11/154,904
• Publication Number:
  US 20060287866A1
• Time in Patent Office: 2,392 Days
• Field of Search: None
• US Class Current: 704/275
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams

Abstract

Methods, systems, and computer program products are provided for modifying a grammar of a hierarchical multimodal menu that include monitoring a user invoking a speech command in a first tier grammar, and adding the speech command to a second tier grammar in dependence upon the frequency of the user invoking the speech command. Adding the speech command to a second tier grammar may be carried out by adding the speech command to a higher tier grammar or by adding the speech command to a lower tier grammar. Adding the speech command to a second tier grammar may include storing the speech command in a grammar cache in the second tier grammar.

Claims

1. A computer implemented method for modifying a grammar of a hierarchical multimodal menu comprising a plurality of tiers including a higher tier and a lower tier in a voice-enabled computing environment, the method being performed by at least one computer of the voice-enabled computing environment and comprising:

in response to receiving a first speech input from a user while the user is navigating the menu at the higher tier, comparing the first speech input to commands of a limited higher-tier grammar associated with the higher tier, the limited higher-tier grammar including commands that can be invoked when the user is navigating at the higher tier and cannot be invoked when the user is navigating at least one other tier of the hierarchical multimodal menu;

monitoring the user invoking a speech command of a limited lower-tier grammar associated with the lower tier, the limited lower-tier grammar including commands that can be invoked when the user is navigating at the lower tier, wherein the speech command is associated with an action; and

adding the speech command to the limited higher-tier grammar in dependence upon the frequency of the user invoking the speech command such that when the user subsequently navigates the menu at the higher tier, the speech command added to the limited higher-tier grammar from the limited lower-tier grammar may be invoked at the higher tier.

2. The method of claim 1 wherein adding the speech command to the limited higher-tier grammar in dependence upon the frequency of the user invoking the speech command further comprises:

maintaining a use count for the speech command;

including the speech command in the limited higher-tier grammar in response to the value of the use count counter exceeding a value of a use threshold; and

storing the speech command in a grammar cache in the limited higher-tier grammar.

3. The method of claim 1 wherein:

the limited lower-tier grammar is associated with a first GUI menu and the limited higher-tier grammar is associated with a second GUI menu; and

adding the speech command to the limited higher-tier grammar further comprises adding a GUI object associated with the speech command to the second GUI menu.

4. The method of claim 1 wherein the limited lower-tier grammar is not enabled when the limited higher-tier grammar is enabled.

5. The method of claim 1 wherein each command of the limited higher-tier grammar corresponds to a menu option of the higher tier.

6. A system for modifying a grammar of a hierarchical multimodal menu comprising a plurality of tiers including a higher tier and a lower tier in a voice-enabled computing environment, the system comprising:

at least one processor programmed to

in response to receiving a first speech input from a user while the user is navigating the menu at the higher tier, compare the first speech input to commands of a limited higher-tier grammar associated with the higher tier, the limited higher-tier grammar including commands that can be invoked when the user is navigating at the higher tier and cannot be invoked when the user is navigating at least one other tier of the hierarchical multimodal menu;

monitor the user invoking a speech command of a limited lower-tier grammar associated with the lower tier, the limited lower-tier grammar including commands that can be invoked when the user is navigating at the lower tier, wherein the speech command is associated with an action; and

add the speech command to the limited higher-tier grammar in dependence upon the frequency of the user invoking the speech command such that when the user subsequently navigates the menu at the higher tier, the speech command added to the limited higher-tier grammar from the limited lower-tier grammar may be invoked at the higher tier.

7. The system of claim 6 wherein the at least one processor is further programmed to:

maintain a use count for the speech command;

include the speech command in the limited higher-tier grammar in response to the value of the use count counter exceeding a value of a use threshold; and

store the speech command in a grammar cache in the limited higher-tier grammar.

8. The system of claim 6 wherein:

the limited lower-tier grammar is associated with a first GUI menu and the limited higher-tier grammar is associated with a second GUI menu; and

the at least one processor is further programmed to add a GUI object associated with the speech command to the second GUI menu.

9. The system of claim 6 wherein the limited lower-tier grammar is not enabled when the limited higher-tier grammar is enabled.

10. The system of claim 6 wherein each command of the limited higher-tier grammar corresponds to a menu option of the higher tier.

11. At least one computer-readable recording storage device encoded with a plurality of instructions that, when executed by at least one processor, perform a method of modifying a grammar of a hierarchical multimodal menu comprising a plurality of tiers including a higher tier and a lower tier in a voice-enabled computing environment, the method comprising:

in response to receiving a first speech input from a user while the user is navigating the menu at the higher tier, comparing the first speech input to commands of a limited higher-tier grammar associated with the higher tier, the limited higher-tier grammar including commands that can be invoked at the higher tier and cannot be invoked when the user is navigating at least one other tier of the hierarchical multimodal menu;

monitoring the user invoking a speech command of a limited lower-tier grammar associated with the lower tier, the limited lower-tier grammar including commands that can be invoked when the user is navigating at the lower tier, wherein the speech command is associated with an action; and

adding the speech command to the limited higher-tier grammar in dependence upon the frequency of the user invoking the speech command such that when the user subsequently navigates the menu at the higher tier, the speech command added to the limited higher-tier grammar from the limited lower-tier grammar may be invoked at the higher tier.

12. The at least one computer-readable device of claim 11 wherein adding the speech command to a second tier grammar in dependence upon the frequency of the user invoking the speech command further comprises:

maintaining a use count for the speech command;

including the speech command in the limited higher-tier grammar in response to the value of the use count counter exceeding a value of a use threshold; and

storing the speech command in a grammar cache in the limited higher-tier grammar.

13. The at least one computer-readable recording storage device of claim 11 wherein:

the limited lower-tier grammar is associated with a first GUI menu and the limited higher-tier grammar is associated with a second GUI menu; and

adding the speech command to the limited higher-tier grammar further comprises adding a GUI object associated with the speech command to the second GUI menu.

14. The at least one computer-readable recording storage device of claim 11 wherein the limited lower-tier grammar is not enabled when the limited higher-tier grammar is enabled.

15. The at least one computer-readable recording storage device of claim 11 wherein each command of the limited higher-tier grammar corresponds to a menu option of the higher tier.