Disambiguation of contact information using historical and context data

• US 8,688,450 B2
• Filed: 07/10/2012
• Issued: 04/01/2014
• Est. Priority Date: 05/19/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Lloyd, Matthew I., Rusch, Willard Van Tuyl II
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US13/545,744
• Publication Number:
  US 20120278076A1
• Time in Patent Office: 630 Days
• Field of Search: 704/200, 704231-256, 7042561-2568, 704/257
• US Class Current: 704/244
• 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 2015/226 using non-speech characteristics
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 2250/60 logging of communication history, e.g. outgoing or incoming calls, missed calls, messages or URLs

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for disambiguating contact information are described. A method includes determining, for each of multiple communications that were initiated by a user of a mobile device, a time when the communication was initiated or received; determining, for each of multiple contacts associated with the user, a probability associated with the contact based at least on the times when the communications were initiated or received; weighting a contact disambiguation grammar according to the probabilities; and processing audio data using the contact disambiguation grammar to select a particular contact.

Claims

1. A computer-implemented method comprising:

receiving audio data encoding an utterance, and data specifying a time when the utterance was spoken;

determining, for each of multiple communications that were initiated by a user of a mobile device, a time when the communication was initiated or received;

determining, for each of the multiple communications, a similarity score based on a similarity between the time when the communication was initiated or received, and the time when the utterance was spoken;

determining, for each of multiple contacts associated with the user, a probability associated with the contact based at least on the similarity score for the communications that were initiated or received;

weighting a contact disambiguation grammar according to the probabilities; and

processing the audio data using the contact disambiguation grammar to select a particular contact.

2. The method of claim 1, comprising:

receiving a data specifying a date when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a date when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between the date when the communication was initiated or received, and the date when the utterance was spoken.

3. The method of claim 1, comprising:

receiving data specifying a location of the mobile device when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a location of the mobile device when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between the location of the mobile device when communication was initiated or received, and the location of the mobile device when the utterance was spoken.

4. The method of claim 1, comprising:

receiving data specifying a device type of a mobile device used to obtain the utterance;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a device type of the mobile device used to initiate or receive the communication; and

wherein the respective similarity score is determined further based on a similarity between the device type of the mobile device used to initiate or receive the communication, and the device type or the mobile device used to obtain the utterance.

5. The method of claim 1, comprising:

receiving data specifying a type of audio subsystem implemented by a mobile device used to obtain the utterance;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a type of audio subsystem implemented by the mobile device used to initiate or receive the communication; and

wherein the respective similarity score is determined further based on a similarity between the type of audio subsystem implemented by the mobile device used to initiate or receive the communication, and the type of audio subsystem implemented by the mobile device used to obtain the utterance.

6. The method of claim 1, comprising:

receiving data specifying whether the mobile device was docked or holstered when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, whether the mobile device was docked or holstered when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between whether the mobile device was docked or holstered when the communications were initiated or received, and whether the mobile device was docked or holstered when the utterance was spoken.

7. The method of claim 1, comprising:

receiving data specifying whether the mobile device had access to a WiFi connection when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, whether the multiple device had access to a WiFi connection when the communication was initiated or received; and

wherein the respective similarity score is determined further based on whether the mobile device had access to a WiFi connection when the communication was initiated or received, and whether the mobile device had access to a WiFi connection when the utterance was spoken.

8. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving audio data encoding an utterance, and data specifying a time when the utterance was spoken;

determining, for each of multiple communications that were initiated by a user of a mobile device, a time when the communication was initiated or received;

determining, for each of the multiple communications, a similarity score based on a similarity between the time when the communication was initiated or received, and the time when the utterance was spoken;

determining, for each of multiple contacts associated with the user, a probability associated with the contact based at least on the similarity score for the communications that were initiated or received;

weighting a contact disambiguation grammar according to the probabilities; and

processing the audio data using the contact disambiguation grammar to select a particular contact.

9. The system of claim 8, wherein the operations comprise:

receiving data specifying a date when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, as date when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between the date when the communication was initiated or received, and the date when the utterance was spoken.

10. The system of claim 8, wherein the operations comprise:

receiving data specifying a location of the mobile device when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a location of the mobile device when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between the location of the mobile device when the communication was initiated or received, and the location of the mobile device when the utterance was spoken.

11. The system of claim 8, wherein the operations comprise:

receiving data specifying a device type of a mobile device used to obtain the utterance;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a device type of the mobile device used to initiate or receive the communication; and

wherein the respective similarity score is determined further based on a similarity between the device type of the mobile device used to initiate or receive the communication, and the device type of the mobile device used to obtain the utterance.

12. The system of claim 8, wherein the operation comprise:

receiving data specifying a type of audio subsystem implemented by a mobile device used to obtain the utterance;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a type of audio subsystem implemented by the mobile device used to initiate or receive the communication; and

wherein the respective similarity score is determined further based on a similarity between the type of audio subsystem implemented by the mobile device used to initiate or receive the communication, and the type of audio subsystem implemented by the mobile device used to obtain the utterance.

13. The system of claim 8, wherein the operations comprise:

receiving data specifying whether the mobile device was docked or holstered when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, whether the mobile device was docked or holstered when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between whether the mobile device was docked or holstered when the communications were initiated or received, and whether the mobile device was decked or holstered when the utterance was spoken.

14. The system of claim 8, wherein the operations comprise:

receiving data specifying whether the mobile device had access to a WiFi connection when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, whether the mobile device had access to a WiFi connection when the communication was initiated or received; and

wherein the respective similarity score is determined further based on whether the mobile device had access to a WiFi connection when the communication was initiated or received, and whether the mobile device had access to a WiFi connection when the utterance was spoken.

15. A computer-readable storage device storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving audio data encoding an utterance, and data specifying a time when the utterance was spoken;

determining, for each of multiple communications that were initiated by a user of a mobile device, a time when the communication was initiated or received;

determining, for each of the multiple communications, a similarity score based on a similarity between the time when the communication was initiated or received, and the time when the utterance was spoken;

determining, for each of multiple contacts associated with the user, a probability associated with the contact based at least on the similarity score for the communications that were initiated or received;

weighting a contact disambiguation grammar according to the probabilities; and

processing the audio data using the contact disambiguation grammar to select a particular contact.

16. The device of claim 15, wherein the operations comprise:

receiving data specifying a date when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a date when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between the date when the communication was initiated or received, and the date when the utterance was spoken.

17. The device of claim 15, wherein the operations comprise:

receiving data specifying a location of the mobile device when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a location of the mobile device when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between the location of the mobile device when the communication was initiated or received, and the location of the mobile device when the utterance was spoken.

18. The device of claim 15, wherein the operations comprise:

receiving data specifying a device type of a mobile device used to obtain the utterance;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a device type of the mobile device used to initiate or receive the communication; and

wherein the respective similarity score is determined further used on a similarity between the device type of the mobile device used to initiate or receive the communication, and the device type of the mobile device used to obtain the utterance.

19. The device of claim 15, wherein the operations comprise:

receiving data specifying a type of audio subsystem implemented by a mobile device used to obtain the utterance;

determining, for each of the multiple communications that were initiated by the user of the mobile device, a type of audio subsystem implemented by the mobile device used to initiate or receive the communication; and

wherein the respective similarity score is determined further based on a similarity between the type of audio subsystem implemented by the mobile device used to initiate or receive the communication, and the type of audio in subsystem implemented by the mobile device used to obtain the utterance.

20. The device of claim 15, wherein the operations comprise:

receiving data specifying whether the mobile device was docked or holstered when the utterance was spoken;

determining, for each of the multiple communications that were initiated by the user of the mobile device, whether the mobile device was docked or holstered when the communication was initiated or received; and

wherein the respective similarity score is determined further based on a similarity between whether the mobile device was docked or holstered when the communications were initiated or received, and whether the mobile device was docked or holstered when the utterance was spoken.