Voice recognition grammar selection based on context

• US 8,255,224 B2
• Filed: 03/07/2008
• Issued: 08/28/2012
• Est. Priority Date: 03/07/2008
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Singleton, David, Ghosh, Debajit
• Primary Examiner(s): Hudspeth, David R
• Assistant Examiner(s): BAKER, MATTHEW H
• Application Number:
  US12/044,310
• Publication Number:
  US 20090228281A1
• Time in Patent Office: 1,635 Days
• Field of Search: 704231-257
• US Class Current: 704/275
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• 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
• CPC Class Codes: G10L 2015/228 of application context

Abstract

The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Claims

1. A computer-implemented method comprising:

receiving, at a computer system, context information that is identified based on a map that was presented on a first computing device in response to a non-verbal user action that was received as input by the first computing device, wherein the non-verbal user action comprises a user providing a request to obtain the map on the first computing device or the user inputting a search query into an interface provided by the first computing device;

identifying, by the computer system and using the context information, a geographic location that is independent of the geographic location of the first computing device;

identifying, by the computer system, a grammar that is associated with the identified geographic location and that includes a vocabulary with terms that are relevant to the identified geographic location and

outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user, to cause a grammar used to process vocal.

2. The method of claim 1, further comprising selecting a location at the center of the map as the geographic location.

3. The method of claim 2, further comprising selecting the geographic location based on a zoom level of the map.

4. The method of claim 1, wherein the non-verbal user action comprises the user providing the request to obtain the map content on the first computing device, and wherein the map includes viewing text that is associated with the geographic location.

5. The method of claim 1, wherein the non-verbal user action comprises the user inputting the search query into the interface provided by the first computing device, and wherein the search query includes text that is associated with the geographic location.

6. The method of claim 1, further comprising receiving a user identifier associated with the user.

7. The method of claim 6, further comprising identifying a user grammar associated with the user identifier and outputting a user grammar indicator to a voice recognition processor for use in selecting the grammar for voice recognition processing of the vocal input from the user.

8. The method of claim 7, further comprising generating the user grammar based on the user'"'"'s past search history.

9. The method of claim 7, further comprising generating the user grammar based on email associated with the user.

10. The method of claim 1, further comprising receiving a list of non-verbal user actions.

11. The method of claim 10, further comprising identifying an application context based on the list and identifying an application context grammar associated with the application context.

12. The method of claim 11, further comprising outputting an application context identifier for use in selecting the grammar for voice recognition processing of the vocal input from the user.

13. The method of claim 10, wherein the list of non-verbal user actions comprises identifiers associated with a user'"'"'s navigation within an application.

14. The method of claim 13, wherein the list includes application menu items selected by the user.

15. The method of claim 1, further comprising selecting a different grammar if an additional non-verbal action implies a new interest of the user, wherein the different grammar is based on the new interest.

18. The method of claim 15, wherein the non-verbal user action comprises the user providing the request to obtain the map on the first computing device, wherein the map is associated with the identified geographic location

wherein the additional non-verbal action comprises the user providing another request to view a different map on the first computing device, wherein the different map is associated with a different geographic location;

and

wherein the implied new interest of the user comprises an interest in the different geographic location.

16. A computer-implemented method comprising:

receiving, at a computer system, context information that is identified based on a map that was presented on a computing device in response to a non-verbal user action that was received as input by the computing device, wherein the non-verbal user action i) comprises a user providing a request to obtain the map on the computing device or the user inputting a search query into an interface provided by the computing device, and is ii) is unprompted by a voice recognition processor;

deriving, by the computer system, a geographic location based on the context information, wherein the derived geographic location is independent of a current geographic location of the computing device;

identifying, by the computer system, a grammar associated with the geographic location, wherein the identified grammar includes, at least, a vocabulary with terms that are relevant to the geographic location; and

outputting a grammar identifier for use in selecting the grammar to use in processing vocal input from the user, to cause a grammar used to process vocal input for the computing device to be changed to the identified grammar.

19. The method of claim 16, wherein the user action comprises the user inputting the search query into the interface provided by the computing device, and wherein the search query includes text that is associated with the geographic location.

17. A system comprising:

a computer system;

an interface of the computer system to receive context information that is identified based on a map that was presented on a first computing device in response to a non-verbal user action that was received as input by the first computing device, wherein the non-verbal user action comprises a user providing a request to obtain the map on the first computing device or the user inputting a search query into an interface provided by the first computing device, and wherein the context information indicates a geographic location that is independent of a current geographic location of the first computing device;

means for identifying a grammar associated with the geographic location derived from the received context information, wherein the identified grammar includes, at least, a vocabulary with terms that are relevant to the identified geographic location; and

a voice recognition server of the computer system configured to change a grammar that is used to interpret vocal input received from the user to the identified grammar.

20. The system of claim 17, wherein the voice recognition server is further configured to use a different grammar to interpret vocal input received from the user if an additional non-verbal action implies a new interest of the user, wherein the different grammar is based on the new interest.