Disambiguating input based on context

• US 9,053,706 B2
• Filed: 07/20/2011
• Issued: 06/09/2015
• Est. Priority Date: 08/06/2010
• Status: Active Grant

• 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:
  US13/186,877
• Publication Number:
  US 20120035924A1
• Time in Patent Office: 1,420 Days
• Field of Search: 704/275, 704/231, 704/251, 704/270, 704/9
• 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 mobile device, a voice input;

generating, by the mobile device, two or more candidate transcriptions from the voice input;

generating, by the mobile device, sensor data that measures an ambient condition surrounding the mobile device at a time when the voice input is received;

inferring, by the mobile device, a user activity in which a user of the mobile device is engaged when the voice input is received, using the sensor data;

selecting, by the mobile device, one of the two or more candidate transcriptions that corresponds to the user activity; and

performing, by the mobile device, a command that is associated with the selected candidate transcription.

2. The method of claim 1, wherein inferring the user activity comprises inferring that the user of the mobile device is driving in a vehicle.

3. The method of claim 2, wherein inferring the user activity comprises inferring a particular type of vehicle in which the user is travelling.

4. The method of claim 1, wherein generating sensor data comprises receiving, by the mobile device, sensor data that is collected by other devices that are within a predetermined distance of the mobile device, or that are in communication with the mobile device over a network connection.

5. A non-transitory computer-readable memory including instructions that, when executed by a processor, cause performance of operations that comprise:

receiving, by a mobile device, a voice input;

generating, by the mobile device, two or more candidate transcriptions from the voice input;

generating, by the mobile device, sensor data that measures an ambient condition surrounding the mobile device at a time when the voice input is received;

inferring, by the mobile device, a user activity in which a user of the mobile device is engaged when the voice input is received, using the sensor data;

selecting, by the mobile device, one of the two or more candidate transcriptions that corresponds to the user activity; and

performing, by the mobile device, a command that is associated with the selected candidate transcription.

6. The non-transitory computer-readable memory of claim 5, wherein inferring the user activity comprises inferring that the user of the mobile device is driving in a vehicle.

7. The non-transitory computer-readable memory of claim 6, wherein inferring the user activity comprises inferring a particular type of vehicle in which the user is travelling.

8. The non-transitory computer-readable memory of claim 5, wherein generating sensor data comprises receiving, by the mobile device, sensor data that is collected by other devices that are within a predetermined distance of the mobile device, or that are in communication with the mobile device over a network connection.