Granted Patent B2

US 12,401,854 · App. 18/161,358 · Granted Aug 26, 2025

Inventor: Alexander Waibel (Sammamish, WA)

Assignee: Zoom Communications, Inc.

H04N21/47205H04N21/4788

Abstract

Claims (74)

1. A method implemented by a conferencing server, comprising:

receiving a query from a first participant of a communication session regarding whether a media stream corresponding to a manipulated participant of the communication session is manipulated;

transmitting an approval request to the manipulated participant seeking permission from the manipulated participant to reply to the query with whether the media stream is manipulated;

receiving, in response to the approval request, a permission to reply to the query;

identifying a manipulation of the media stream, wherein the manipulation comprises at least one of an accent reduction manipulation or a language translation manipulation;

transmitting, in response to the query, a notification of the manipulation to the first participant;

prompting the first participant to approve or disapprove the manipulation;

receiving, based on the prompting, an approval indication of the manipulation from the first participant;

determining that the approval indication indicates a disapproval of the manipulation; and

transmitting a request to disable the manipulation to the manipulated participant of the communication session.

2. The method of claim 1 , wherein the manipulation is enabled by the manipulated participant.

3. The method of claim 1 , further comprising:

in response to the manipulation not being disabled, disconnecting the manipulated participant from the communication session.

4. The method of claim 1 , wherein the notification of the manipulation includes a degree of the manipulation.

5. The method of claim 1 , wherein identifying the manipulation of the media stream associated with the manipulated participant of the communication session comprises:

obtaining initial images from a camera of a device of the manipulated participant;

obtaining an initial feature based on the initial images;

obtaining current images from the media stream;

obtaining a current feature from the current images; and

obtaining a match score by comparing the initial feature to the current feature.

6. The method of claim 1 , wherein transmitting the notification of the manipulation to the first participant of the communication session comprises:

obtaining initial voice samples from a microphone of a device of the manipulated participant;

obtaining an initial feature based on the initial voice samples;

obtaining current voice samples from the media stream;

obtaining a current feature from the current voice samples; and

obtaining a match score by comparing the initial feature to the current feature.

7. A device, comprising:

a memory; and

a processor, the processor configured to execute instructions stored in the memory to:

receive a query from a first participant of a communication session regarding whether a media stream corresponding to a manipulated participant of the communication session is manipulated;

transmit an approval request to the manipulated participant seeking permission from the manipulated participant to reply to the query with whether the media stream is manipulated;

receive, in response to the approval request, a permission to reply to the query;

identify a manipulation of the media stream, wherein the manipulation comprises at least one of an accent reduction manipulation or a language translation manipulation;

transmit, in response to the query, a notification of the manipulation to the first participant;

prompt the first participant to approve or disapprove the manipulation;

receive, based on the prompt, an approval indication of the manipulation from the first participant;

determine that the approval indication indicates a disapproval of the manipulation; and

transmit a request to disable the manipulation to the manipulated participant of the communication session.

8. The device of claim 7 , wherein the manipulation is enabled by the manipulated participant.

9. The device of claim 7 , wherein the processor is further configured to execute instructions stored in the memory to:

in response to the manipulation not being disabled, disconnect the manipulated participant from the communication session.

10. The device of claim 7 , wherein the notification of the manipulation comprises a degree of the manipulation.

11. The device of claim 7 , wherein the instructions to identify the manipulation of the media stream associated with the manipulated participant of the communication session comprise instructions to:

obtain initial images from a camera of a device of the manipulated participant;

obtain an initial feature based on the initial images;

obtain current images from the media stream;

obtain a current feature from the current images; and

obtain a match score by comparing the initial feature to the current feature.

12. The device of claim 7 , wherein the instructions to transmit the notification of the manipulation to the first participant of the communication session comprise instructions to:

obtain initial voice samples from a microphone of a device of the manipulated participant;

obtain an initial feature based on the initial voice samples;

obtain current voice samples from the media stream;

obtain a current feature from the current voice samples; and

obtain a match score by comparing the initial feature to the current feature.

13. A non-transitory computer-readable storage medium of a conferencing server storing instructions operable to cause one or more processors to perform operations, comprising:

receiving a query from a first participant of a communication session regarding whether a media stream corresponding to a manipulated participant of the communication session is manipulated;

transmitting an approval request to the manipulated participant seeking permission from the manipulated participant to reply to the query with whether the media stream is manipulated;

receiving, in response to the approval request, a permission to reply to the query;

identifying a manipulation of the media stream, wherein the manipulation comprises at least one of an accent reduction manipulation or a language translation manipulation;

transmitting, in response to the query, a notification of the manipulation to the first participant;

prompting the first participant to approve or disapprove the manipulation;

receiving, based on the prompting, an approval indication of the manipulation from the first participant;

determining that the approval indication indicates a disapproval of the manipulation; and

transmitting a request to disable the manipulation to the manipulated participant of the communication session.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the manipulation is enabled by the manipulated participant, the first participant is a participant other than the manipulated participant.

15. The non-transitory computer-readable storage medium of claim 13 , wherein the operations further comprise:

in response to the manipulation not being disabled, disconnecting the manipulated participant from the communication session.

16. The non-transitory computer-readable storage medium of claim 13 , wherein the notification of the manipulation comprises a degree of the manipulation.

17. The non-transitory computer-readable storage medium of claim 13 , wherein transmitting the notification of the manipulation to the first participant of the communication session comprises:

obtaining initial media from a device of the manipulated participant, wherein the initial media comprises at least one of initial images or initial voice samples;

obtaining an initial feature based on the initial media;

obtaining current media from the media stream;

obtaining a current feature from the current media; and

obtaining a match score by comparing the initial feature to the current feature.

Assignments (2)

Continuity (1)

References Cited (33)