Dynamic Grammar for Voice-Enabled Applications

• US 20070179778A1
• Filed: 01/16/2007
• Published: 08/02/2007
• Est. Priority Date: 02/07/2002
• Status: Abandoned Application

• Current Assignee: SAP AG (SAP SE)
• Original Assignee: SAP AG (SAP SE)
• Inventors: Weng, Jie, Raiyani, Samir, Swan, Richard, Gong, Li, Vogler, Hartmut
• Application Number:
  US11/623,455
• Publication Number:
  US 20070179778A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4931 Directory assistance systems
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A graphical user interface may include a form with a plurality of fields, each field associated with a predetermined category. Each category may have its own, independent, discrete grammar associated therewith, and the independent grammars may be individually activated, simultaneously with their respective categories. In this way, a voice-recognition system that is inputting spoken data for each of the fields may have a restricted grammar to search when attempting to match a particular voice input with an entry for a particular field in the form. Moreover, a global grammar that is active with any one of the independent grammars may be used to move between the fields or perform other high-level functionality not associated with any one of the independent grammars.

Claims

1. A method comprising:

activating a global grammar;

accessing first and second specific grammars;

outputting first and second input fields, the first and second input fields being associated with the first and second specific grammars, respectively;

receiving a voice command;

matching the voice command with a first user selection indicative of the first input field using the global grammar;

activating the first specific grammar based upon matching the voice command with the first user selection, the first specific grammar being concurrently activated with the global grammar;

deactivating the second specific grammar concurrently with activating the first specific grammar;

highlighting the first input field based upon activating the first specific grammar;

receiving a first user input;

matching the first user input with a first word in the first specific grammar;

populating the first input field with the first word;

receiving a second user selection indicative of the second input field;

activating the second specific grammar based upon receiving the second user selection, the second specific grammar being concurrently activated with the global grammar;

highlighting the second input field based on activating the second specific grammar;

deactivating the first specific grammar concurrently with activating the second specific grammar;

receiving a second user input;

matching the second user input with a second word in the second specific grammar; and

populating the second input field with the second word.

2. A method comprising:

activating a global grammar;

accessing first and second specific grammars;

outputting first and second input fields, the first and second input fields being associated with the first and second specific grammars, respectively;

receiving a first user selection indicative of the first input field;

activating the first specific grammar based upon receiving the first user selection;

deactivating the second specific grammar based upon receiving the first user selection;

receiving a second user selection indicative of the second input field;

activating the second specific grammar based upon receiving the second user selection; and

deactivating the first specific grammar based upon receiving the second user selection.

3. The method of claim 2,

wherein the first and second specific grammars are not concurrently activated with each other, and

wherein the first or second specific grammars are concurrently activated with the global grammar.

4. The method of claim 2, wherein the global grammar further comprises a field navigation command, a browser navigation command, or a device reset command.

5. The method of claim 2, wherein the first specific grammar comprises a city name grammar, a state name grammar, a street address grammar, a first name grammar, or a last name grammar.

6. The method of claim 2, wherein the first and second specific grammars are separate, discrete, and independent.

7. The method of claim 2, wherein at least one word is replicated in each of the first and second specific grammars.

8. The method of claim 2, wherein the first specific grammar is activated concurrently with deactivating the second specific grammar.

9. The method of claim 2, further comprising:

receiving a user input;

match the user input with a word in the activated specific grammar; and

populating the user input field associated with the activated specific grammar with the word.

10. The method of claim 2, further comprising outputting an indication of the activated specific grammar.

11. The method of claim 10, wherein outputting the indication of the activated specific grammar further comprises displaying a field within a web page.

12. The method of claim 10, wherein outputting the indication of the activated specific grammar further comprises audibly outputting the input using a voice.

13. The method of claim 10, wherein outputting the indication of the activated specific grammar further comprises highlighting the input field associated with the activated specific grammar.

14. The method of claim 2, wherein outputting the first and second input fields further comprises displaying the first and second input fields on a web page.

15. The method of claim 2, wherein receiving the first user selection further comprises:

receiving a voice command; and

matching the voice command with the first user selection using the global grammar.

16. The method of claim 2, wherein receiving the first user selection indicative of the first input field further comprises selecting the first input field using an input device.

17. The method of claim 2, wherein the global grammar is included within the first and second specific grammars.

18. A device comprising

a storage medium configured to store a global grammar and first and second specific grammars;

a grammar activation and deactivation module configured to;

activate the global grammar,

output first and second input fields, the first and second input fields being associated with the first and second specific grammars, respectively,

receive a first user selection indicative of the first input field,

activate the first specific grammar based upon receiving the first user selection,

deactivating the second specific grammar based upon receiving the first user selection,

receiving a second user selection indicative of the second input field,

activating second specific grammar based upon receiving the second user selection, and

deactivating the first specific grammar based upon receiving the second user selection.

19. The device of claim 18, further comprising a voice recognition module configured to:

receive a user input; and

match the user input with a word of the activated specific grammar.

20. The device of claim 18, further comprising an input indication module configured to output an indication of the activated specific grammar.