Keyword determinations from voice data

• US 9,679,570 B1
• Filed: 08/17/2015
• Issued: 06/13/2017
• Est. Priority Date: 09/23/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Edara, Kiran K.
• Primary Examiner(s): Guerra-Erazo, Edgar
• Application Number:
  US14/828,220
• Time in Patent Office: 666 Days
• Field of Search: None
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

Topics of potential interest to a user, useful for purposes such as targeted advertising and product recommendations, can be extracted from voice content produced by a user. A computing device can capture voice content, such as when a user speaks into or near the device. One or more sniffer algorithms or processes can attempt to identify trigger words in the voice content, which can indicate a level of interest of the user. For each identified potential trigger word, the device can capture adjacent audio that can be analyzed, on the device or remotely, to attempt to determine one or more keywords associated with that trigger word. The identified keywords can be stored and/or transmitted to an appropriate location accessible to entities such as advertisers or content providers who can use the keywords to attempt to select or customize content that is likely relevant to the user.

Claims

1. A computer-implemented method, comprising:

receiving speech data;

determining at least one trigger word in the speech data;

generating text data by performing one or more speech recognition processes on a portion of the speech data that includes the at least one trigger word and that satisfies a predetermined factor;

determining at least one keyword in the text data;

determining information based at least in part upon two or more of past behavior data associated with a user profile, a received update from another source, or another keyword associated with the user profile; and

determining content to be provided based at least in part upon the at least one trigger word, the at least one keyword, and the information.

2. The computer-implemented method of claim 1, further comprising providing the content within an advertisement or a recommendation.

3. The computer-implemented method of claim 1, further comprising providing the content as audio data with a user-configurable volume.

4. The computer-implemented method of claim 1, further comprising providing the content as visual data.

5. The computer-implemented method of claim 1, further comprising:

capturing the speech data to during a communication session.

6. The computer-implemented method of claim 5, further comprising providing the content using a second computing device.

7. The computer-implemented method of claim 6, further comprising:

determining the user profile based on an association between a computing device used to capture the speech data and the user profile.

8. The computer-implemented method of claim 1, further comprising causing the at least one trigger word to be stored by a first computing device or at least one remote data store.

9. The computer-implemented method of claim 8, further comprising comparing the at least one trigger word with a plurality of trigger words and variants of the plurality of trigger words.

10. The computer-implemented method of claim 9, further comprising:

determining additional information associated with the speech data, the additional information including at least one of a time stamp, geographic coordinates, identity information associated with the user profile, a context of the speech data, or a priority of the at least one keyword.

11. A system, comprising:

at least one processor; and

at least one memory device including instructions that, when executed by the at least one processor, cause the system to;

receive speech data;

determine at least one trigger word in the speech data;

generate text data by performing one or more speech recognition processes on a portion of the speech data that includes the at least one trigger word and that satisfies a predetermined factor;

determine at least one keyword in the text data;

determine information based at least in part upon two or more of past behavior data associated with a user profile, a received update from another source, or another keyword associated with the user profile; and

determine content to be provided based at least in part upon the at least one trigger word, the at least one keyword, and the information.

12. The system of claim 11, wherein the content is an advertisement or a recommendation.

13. The system of claim 11, wherein the content is provided as audio data with a user-configurable volume.

14. The system of claim 11, wherein the content is provided as visual data.

15. The system of claim 11, wherein the speech data is captured using a first computing device during a communication session.

16. The system of claim 15, wherein the content is provided using a second computing device.

17. The system of claim 15, wherein the first computing device is associated with the user profile.

18. The system of claim 11, wherein the at least one trigger word corresponds to a plurality of trigger words stored by a first computing device or at least one remote data store.

19. The system of claim 11, wherein the instructions, when executed by the at least one processor, further cause the system to:

compare the at least one trigger word with a plurality of trigger words and variants of the plurality of trigger words.

20. The system of claim 11, wherein the instructions when executed by the at least one processor, further cause the system to:

determine additional information associated with the speech data, the additional information including at least one of a time stamp, geographic coordinates, identity information associated with the user profile, a context of the speech data, or a priority of the at least one keyword.