Assisted speech recognition

Patent metadata

Field	Value
Publication number	US-11810573-B2
Application number	US-202117239349-A
Country	US
Kind code	B2
Filing date	Apr 23, 2021
Priority date	Apr 23, 2021
Publication date	Nov 7, 2023
Grant date	Nov 7, 2023

Abstract

Systems, apparatuses, and methods are described for assisting speech recognition processing. If speech recognition processing of speech input by an individual does not yield a recognized result, for example, if speech is from an individual with compromised speech, an indication may be sent to a device associated with another person that can assist. The other person may provide, via that device, additional input that indicates the meaning of the speech input. Based on this additional input, an assisted speech recognition result may be determined.

First claim

The invention claimed is:

1. A method comprising:
receiving, for audio recognition processing, a first audio communication from a first user, wherein the first audio communication comprises a request for performance of an operation by a first device;
determining that the first audio communication cannot be recognized;
receiving, based on the determining that the first audio communication cannot be recognized, an indication that the first user requests audio recognition assistance;
sending, based on the receiving the indication that the first user requests audio recognition assistance, a message comprising at least a portion of the first audio communication to a second device associated with a second user, wherein the second user is associated with recognizing audio from the first user; and
receiving, from the second device, a second audio communication that comprises a recognizable version of the first audio communication.

2. The method of claim 1 , wherein the operation comprises output of one or more content items, the method further comprising:
causing, based on the received second audio communication, the first device to perform the operation.

3. The method of claim 1 , further comprising:
updating, based on the received second audio communication and the first audio communication, data used to perform speech recognition processing of the first audio communication.

4. The method of claim 1 , wherein the message causes the second device to output a user interface for providing an indication of the operation.

5. The method of claim 1 , further comprising:
determining, based on the determining that the first audio communication cannot be recognized and on data indicating one or more computing devices associated with a source of the first audio communication, the second device.

6. The method of claim 1 , wherein the message further comprises an indication that assistance of the second user is requested for the first audio communication.

7. The method of claim 1 , wherein the first device is located in a premises and the second device is located remote from the premises.

8. The method of claim 1 , further comprising:
determining, before the sending of the message to the second device, a speech recognition assistance mode associated with the first device.

9. The method of claim 1 , further comprising:
performing speech recognition processing of the second audio communication; and
determining that a result, of the speech recognition processing of the second audio communication, corresponds to a valid input to the first device.

10. A method comprising:
determining, by a computing device, that an audio communication associated with a request for output of one or more content items cannot be recognized;
receiving, by the computing device and from a source of the audio communication, a first indication that audio recognition assistance is requested;
determining, based on the receiving the first indication that audio recognition assistance is requested, on the determining that the audio communication cannot be recognized, and on data indicating one or more other computing devices associated with the source of the audio communication, a second computing device;
causing sending of the audio communication to the determined second computing device;
receiving, from the second computing device, a second indication of the one or more content items; and
causing, based on the received second indication, output of the one or more content items.

11. The method of claim 10 , further comprising:
updating, based on the received second indication and the audio communication, data used to perform speech recognition processing of the audio communication.

12. The method of claim 10 , wherein the causing sending of the audio communication comprises causing the second computing device to output a user interface for providing the second indication of the one or more content items.

13. The method of claim 10 , wherein the causing sending of the audio communication further comprises causing sending of an indication that assistance of the determined second computing device is requested for the audio communication.

14. The method of claim 10 , wherein the received second indication comprises a second audio communication, the method further comprising:
performing speech recognition processing of the second audio communication; and
determining that a result, of the speech recognition processing of the second audio communication, corresponds to a valid input to a device associated with the audio communication.

15. The method of claim 10 , further comprising:
determining, before the causing the sending of the audio communication to the second computing device, a speech recognition assistance mode associated with the audio communication.

16. A method comprising:
receiving, for speech recognition processing, an audio communication comprising a request, by a first user, for performance of an operation by a first device;
determining that the audio communication cannot be recognized;
receiving, based on the determining that the audio communication cannot be recognized, an indication that the first user requests audio recognition assistance;
based on the indication that the first user requests audio recognition assistance and the determining that the audio communication cannot be recognized, causing output, via a second device associated with a second user, of a user interface for providing additional information about the audio communication;
receiving, from the second device, the additional information; and
causing, based on the received additional information, performance of the operation.

17. The method of claim 16 , wherein the operation comprises output of one or more content items.

18. The method of claim 16 , further comprising:
updating, based on the received additional information and the audio communication, data used to perform speech recognition processing of the audio communication.

19. The method of claim 16 , further comprising:
determining, based on the determining that the audio communication cannot be recognized and on data indicating one or more computing devices associated with a source of the audio communication, the second device.

20. The method of claim 16 , further comprising:
determining, before the causing the output of the user interface, a speech recognition assistance mode associated with the first device.

21. The method of claim 1 , further comprising:
determining, based on the first audio communication from the first user, an audio recognition result;
causing output, via a user interface, of text indicating the audio recognition result; and
causing output, via the user interface, of at least one option selectable by the first user that indicates that the the audio recognition result is incorrect and that the first user requests audio recognition assistance from the second user.

22. The method of claim 1 , further comprising:
storing data indicating users that are able to understand speech of the first user; and
determining, based on the data indicating users that are able to understand speech of the first user, the second user.

23. The method of claim 1 , wherein the second user comprises at least one of: a family member, a medical professional, or a person trained in speech recognition.

Assignees

• Comcast Cable Comm Llc

Inventors

• Loftus Daniel

Classifications

• G10L15/30 Primary

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

• G10L15/22 Primary

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

• G10L15/08

  Speech classification or search · CPC title

• G10L2015/228

  of application context · CPC title

• G10L15/32

  Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems · CPC title