Disambiguating input based on context

• US 9,401,147 B2
• Filed: 06/08/2015
• Issued: 07/26/2016
• Est. Priority Date: 08/06/2010
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Jitkoff, John Nicholas, LeBeau, Michael J.
• Primary Examiner(s): Han, Qi
• Application Number:
  US14/733,073
• Publication Number:
  US 20150269937A1
• Time in Patent Office: 414 Days
• Field of Search: 704/235, 704/231, 704/251, 704/1, 704/9, 704/257, 704/270, 704/275
• US Class Current: 1/1
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04M 1/72454 according to context-related or environment-related conditions
• CPC Class Codes: H04M 1/72457 according to geographic location

Abstract

In one implementation, a computer-implemented method includes receiving, at a mobile computing device, ambiguous user input that indicates more than one of a plurality of commands; and determining a current context associated with the mobile computing device that indicates where the mobile computing device is currently located. The method can further include disambiguating the ambiguous user input by selecting a command from the plurality of commands based on the current context associated with the mobile computing device; and causing output associated with performance of the selected command to be provided by the mobile computing device.

Claims

1. A computer-implemented method, comprising:

receiving, by a computing system, voice input that was captured by a microphone of a mobile computing device;

interpreting, by the computing system, the voice input using a speech recognition system that is configured to convert the voice input to text;

identifying, by the computing system, a portion of the voice input as being ambiguous due to the portion of the voice input being able to be represented by either of two or more homophones or homonyms;

identifying, by the computing system, one or more geographic locations of the mobile computing device, the mobile computing device having received one or more wireless signals from one or more external transmitting devices and from which the mobile computing device was able to determine the one or more geographic locations;

applying, by the computing system, the portion of the voice input that is able to be represented by either of the two or more homophones or homonyms to one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms as a selected homophone or homonym that represents the portion of the voice input; and

outputting, by the computing system and in response to the computing system having selected the one of the two or more homophones or homonyms as the selected homophone or homonym, the selected homophone or homonym to a computer application or computer service that is associated with the voice input.

2. The computer-implemented method of claim 1, wherein:

the one or more wireless signals that the mobile computing device received from the one or more external transmitting devices are multiple wireless signals that the mobile computing device received from multiple global positioning system satellites, and

identifying the one or more geographic locations of the mobile computing device includes using a global positioning system unit of the mobile computing device to identify the one or more geographic locations.

3. The computer-implemented method of claim 1, wherein:

the one or more wireless signals that the mobile computing device received from the one or more external transmitting devices is one or more wireless signals that the mobile computing device received from one or more base stations, and

identifying the one or more geographic locations of the mobile computing device includes using base station transmitting antenna identification or multiple base station triangulation to identify the one or more geographic locations.

4. The computer-implemented method of claim 1, wherein:

the one or more geographic locations is multiple geographic locations; and

applying the portion of the voice input to the one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms includes the computing system determining that a direction of travel, as identified by the multiple geographic locations, is toward a geographic location that is associated with the selected one of the two homophones or homonyms.

5. The computer-implemented method of claim 1, wherein applying the portion of the voice input to the one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms includes determining that the one or more geographic locations of the mobile computing device are within a predetermined distance to a geographic location that is identified by a contact record from a contact list and that is associated with the selected one of the two homophones or homonyms.

6. The computer-implemented method of claim 1, wherein:

the one or more geographic locations is multiple geographic locations; and

applying the portion of the voice input to the one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms includes determining that a direction of travel, as identified by the multiple geographic locations, is toward a geographic location that is identified by a contact record from a contact list and that is associated with the selected one of the two homophones or homonyms.

7. The computer-implemented method of claim 1, wherein:

the one or more geographic locations is multiple geographic locations; and

applying the portion of the voice input to the one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms includes determining that the multiple geographic locations indicate that the mobile computing device is traveling with a rate of speed that exceeds a predefined rate of speed in order to select one of the two or more homophones or homonyms that is associated with travel in a vehicle.

8. The computer-implemented method of claim 1, wherein outputting the selected homophone or homonym to the computer application or service that is associated with the voice input includes the computing system sending a transcription of the voice input, including text of the selected homophone or homonym, to the mobile computing device.

9. A non-transitory computer-readable medium encoded with instructions that, when executed, operate to cause one or more processors to perform operations comprising:

receiving, by a computing system, voice input that was captured by a microphone of a mobile computing device;

interpreting, by the computing system, the voice input using a speech recognition system that is configured to convert the voice input to text;

identifying, by the computing system, a portion of the voice input as being ambiguous due to the portion of the voice input being able to be represented by either of two or more homophones or homonyms;

identifying, by the computing system, one or more geographic locations of the mobile computing device, the mobile computing device having received one or more wireless signals from one or more external transmitting devices and from which the mobile computing device was able to determine the one or more geographic locations;

applying, by the computing system, the portion of the voice input that is able to be represented by either of the two or more homophones or homonyms to one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms as a selected homophone or homonym that represents the portion of the voice input; and

outputting, by the computing system and in response to the computing system having selected the one of the two or more homophones or homonyms as the selected homophone or homonym, the selected homophone or homonym to a computer application or computer service that is associated with the voice input.

10. The non-transitory computer-readable medium of claim 9, wherein:

the one or more wireless signals that the mobile computing device received from the one or more external transmitting devices are multiple wireless signals that the mobile computing device received from multiple global positioning system satellites, and

identifying the one or more geographic locations of the mobile computing device includes using a global positioning system unit of the mobile computing device to identify the one or more geographic locations.

11. The non-transitory computer-readable medium of claim 9, wherein:

the one or more wireless signals that the mobile computing device received from the one or more external transmitting devices is one or more wireless signals that the mobile computing device received from one or more base stations, and

identifying the one or more geographic locations of the mobile computing device includes using base station transmitting antenna identification or multiple base station triangulation to identify the one or more geographic locations.

12. The non-transitory computer-readable medium of claim 9, wherein:

the one or more geographic locations is multiple geographic locations; and

applying the portion of the voice input to the one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms includes the computing system determining that a direction of travel, as identified by the multiple geographic locations, is toward a geographic location that is associated with the selected one of the two homophones or homonyms.

13. The non-transitory computer-readable medium of claim 9, wherein applying the portion of the voice input to the one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms includes determining that the one or more geographic locations of the mobile computing device are within a predetermined distance to a geographic location that is identified by a contact record from a contact list and that is associated with the selected one of the two homophones or homonyms.

14. The non-transitory computer-readable medium of claim 9, wherein:

the one or more geographic locations is multiple geographic locations; and

applying the portion of the voice input to the one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms includes determining that a direction of travel, as identified by the multiple geographic locations, is toward a geographic location that is identified by a contact record from a contact list and that is associated with the selected one of the two homophones or homonyms.

15. The non-transitory computer-readable medium of claim 9, wherein:

the one or more geographic locations is multiple geographic locations; and

applying the portion of the voice input to the one or more rules that use the one or more geographic locations of the mobile computing device to select one of the two or more homophones or homonyms includes determining that the multiple geographic locations indicate that the mobile computing device is traveling with a rate of speed that exceeds a predefined rate of speed in order to select one of the two or more homophones or homonyms that is associated with travel in a vehicle.

16. The non-transitory computer-readable medium of claim 9, wherein outputting the selected homophone or homonym to the computer application or service that is associated with the voice input includes the computing system sending a transcription of the voice input, including text of the selected homophone or homonym, to the mobile computing device.