Navigating content utilizing speech-based user-selectable elements

Patent metadata

Field	Value
Publication number	US-9280973-B1
Application number	US-201213532626-A
Country	US
Kind code	B1
Filing date	Jun 25, 2012
Priority date	Jun 25, 2012
Publication date	Mar 8, 2016
Grant date	Mar 8, 2016

Abstract

In a content browsing environment, a system analyzes content to identify audio commands to be made available to users. The audio commands may be chosen so that they are easily differentiable from each other when using machine-based speech recognition techniques. When the content is displayed, the system monitors a user's speech to detect user utterances corresponding to the audio commands and performs content navigation in response to the user utterances.

First claim

What is claimed is:

1. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform acts comprising:
receiving a designation of content having user-selectable elements;
analyzing the content to identify an audio command corresponding to one or more user-selectable elements of the user-selectable elements, the audio command being identified based at least in part on an acoustic differentiation between the audio command and a different audio command meeting or exceeding a threshold;
receiving a signal associated with an utterance of a user, the signal generated by a microphone associated with a device;
analyzing the signal associated with the utterance to determine the audio command; and
responding to the utterance in accordance with a user-selectable element of the one or more user-selectable elements corresponding to the audio command, the responding including
causing information associated with the audio command to be visually output via a projector associated with the device.

2. The one or more non-transitory computer-readable media of claim 1 , wherein analyzing the content to identify the audio command comprises identifying words of the content based at least in part on the acoustic differentiation between the audio command and the different audio command by a machine-implemented speech recognizer.

3. The one or more non-transitory computer-readable media of claim 1 , wherein analyzing the content to identify the audio command comprises selecting text from the content.

4. The one or more non-transitory computer-readable media of claim 1 , wherein analyzing the content to identify the audio command comprises selecting text associated with the one or more user-selectable elements.

5. The one or more non-transitory computer-readable media of claim 1 , wherein at least one user-selectable element of the user-selectable elements is associated with an image, and wherein analyzing the content to identify the audio command comprises performing image recognition to identify one or more words that correspond to the image.

6. The one or more non-transitory computer-readable media of claim 1 , wherein at least one user-selectable element of the user-selectable elements is associated with audio, and wherein analyzing the content to identify the audio command comprises performing speech recognition to identify one or more words that correspond to the audio.

7. The one or more non-transitory computer-readable media of claim 1 , the acts further comprising displaying textual indications of the audio command in conjunction with the content.

8. The one or more non-transitory computer-readable media of claim 1 , wherein an individual user-selectable element of the user-selectable elements is associated with non-textual media, and wherein analyzing the content to identify the audio command comprises recognizing one or more words indicated by the non-textual media.

9. A method, comprising:
receiving, by one or more computing devices, a request designating content, wherein the content has a user-selectable element;
determining, by at least one computing device of the one or more computing devices, an audio command corresponding to the user-selectable element, the audio command being determined based at least in part on an acoustic differentiation between the audio command and a different audio command meeting or exceeding a threshold;
associating, by at least one computing device of the one or more computing devices, the audio command with the user-selectable element; and
causing information associated with audio command to be visually output by a projector associated with the second device.

10. The method of claim 9 , further comprising:
identifying the audio command in response to a user utterance; and
responding to the user utterance in accordance with the user-selectable element that corresponds to the audio command.

11. The method of claim 9 , wherein determining the audio command is performed based at least in part on the acoustic differentiation between the audio command and the different audio command by a machine-implemented speech recognizer.

12. The method of claim 9 , wherein determining the audio command comprises selecting text from the content.

13. The method of claim 9 , wherein determining the audio command comprises selecting text from the user-selectable element.

14. The method of claim 9 , wherein the user-selectable element is associated with audio, and wherein determining the audio command comprises performing speech recognition to identify one or more words that correspond to the audio.

15. The method of claim 9 , wherein the user-selectable element is associated with an image, and wherein determining the audio command comprises performing image recognition to identify one or more words that correspond to the image.

16. The method of claim 9 , wherein the user-selectable element is associated with non-textual media, and wherein determining the audio command comprises recognizing one or more words indicated by the non-textual media.

17. The method of claim 9 , further comprising causing display of textual indications of the audio commands in conjunction with the content.

18. A system comprising:
one or more processors;
one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
receiving a request that specifies a user utterance with regard to content having user-selectable elements;
analyzing the content to identify an audio command corresponding to one or more user-selectable elements of the user-selectable elements, the audio command being identified based at least in part on an acoustic differentiation between the audio command and a different audio command meeting or exceeding a threshold;
selecting the audio command based at least in part on the user utterance; and
responding to the request in accordance with a user-selectable element of the one or more user-selectable elements corresponding to the audio command, the responding including
causing information associated with the audio command to be visually output via a projector associated with a device.

19. The system of claim 18 , wherein the request identifies at least a portion of the content.

20. The system of claim 18 , wherein analyzing the content to identify the audio command comprises selecting words of the content based at least in part on differentiability of the words by a machine-implemented speech recognizer.

21. The system of claim 18 , wherein analyzing the content to identify the audio command comprises selecting text from the content.

22. The system of claim 18 , wherein analyzing the content to identify the audio command comprises selecting text associated with the one or more user-selectable elements of the user-selectable elements.

23. The system of claim 18 , wherein at least one user-selectable element of the user-selectable elements is associated with audio, and wherein analyzing the content to identify the audio command comprises performing speech recognition to identify one or more words that correspond to the audio.

24. The system of claim 18 , wherein at least one user-selectable element of the user-selectable elements is associated with an image, and wherein analyzing the content to

Assignees

• Soyannwo Olusanya T
• Sadek Ramy S
• Crump Edward Dietz
• Raghunathan Siddarth
• Yan Renwei
• Amazon Tech Inc

Inventors

• Soyannwo Olusanya T
• Sadek Ramy S
• Crump Edward Dietz
• Raghunathan Siddarth
• Yan Renwei

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/30 Primary

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L2015/228

  of application context · CPC title