Granted Patent B2

US 12,537,704 · App. 17/513,226 · Granted Jan 27, 2026

Inventor: Nick Swerdlow (Santa Clara, CA)

Assignee: Zoom Communications, Inc.

H04L12/1822G10L15/26G10L17/00H04M3/563

Abstract

Claims (71)

1 . A method, comprising:

generating, using a transcription engine accessing audio of an ongoing conference implemented by a conferencing software and including participants, a real-time transcript of a portion of the ongoing conference, wherein generating the real-time transcript comprises:

determining that audio accessed by the transcription engine includes speech from a person who is not a participant of the ongoing conference, wherein the speech from the person is included in audio data associated with one of the participants; and

in response to determining that the audio accessed by the transcription engine includes the speech from the person who is not a participant of the ongoing conference, preventing the speech from the person from being included in the real-time transcript; and

responsive to detecting that a topic-of-interest associated with a user who is not a current participant of the ongoing conference is referenced within the real-time transcript:

presenting, via the conferencing software, a real-time voting interface to at least some participants of the ongoing conference;

identifying respective votes of at least some of the participants of the ongoing conference, wherein each of the respective votes indicates whether a notification indicative of the topic-of-interest is to be transmitted to the user responsive to detecting that the topic-of-interest is associated with the user, wherein each of the respective votes indicates whether a notification indicative of the topic-of-interest is to be transmitted to the user responsive to detecting that the topic-of-interest is associated with the user, and wherein the respective votes are collected in real-time from the participants of the ongoing conference via the real-time voting interface;

determining, based on a voting rule, whether the respective votes indicate to transmit the notification; and

in response to determining that the respective votes indicate to transmit the notification, transmitting the notification indicative of the topic-of-interest and the ongoing conference to the user.

2 . The method of claim 1 , further comprising:

terminating the ongoing conference in response to a termination request from a user privileged to terminate the ongoing conference.

3 . The method of claim 1 , wherein the notification includes a user interface element configured for accessing the ongoing conference.

4 . The method of claim 1 , wherein the topic-of-interest is associated with the user based on calendar information of the user.

5 . The method of claim 1 , wherein the topic-of-interest is associated with the user based on documents obtained from the user.

6 . The method of claim 1 , further comprising:

receiving, from another participant, an indication to disable a transcription of speech of the another participant;

stopping transcription of the speech of the another participant while the transcription is disabled; and

transmitting the speech of the another participant to other participants while the transcription is disabled.

7 . The method of claim 1 , further comprising:

receiving a message from the user; and

presenting the message to participants of the ongoing conference without joining the user to the ongoing conference.

8 . A device, comprising:

a memory; and

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

generate, using a transcription engine accessing audio of an ongoing conference implemented by a conferencing software and including participants, a real-time transcript of a portion of the ongoing conference, wherein to generate the real-time transcript comprises to:

determine that audio accessed by the transcription engine includes speech from a person who is not a participant of the ongoing conference, wherein the speech from the person is included in audio data associated with one of the participants; and

in response to determining that the audio accessed by the transcription engine includes the speech from the person who is not a participant of the ongoing conference, prevent the speech from the person from being included in the real-time transcript; and

responsive to detecting that a topic-of-interest associated with a user who is not a current participant of the ongoing conference is referenced within the real-time transcript:

present, via the conferencing software, a real-time voting interface to at least some participants of the ongoing conference;

identify respective votes of at least some of the participants of the ongoing conference, wherein each of the respective votes indicates whether a notification indicative of the topic-of-interest is to be transmitted to the user responsive to detecting that the topic-of-interest is associated with the user, wherein each of the respective votes indicates whether a notification indicative of the topic-of-interest is to be transmitted to the user responsive to detecting that the topic-of-interest is associated with the user, and wherein the respective votes are collected in real-time from the participants of the ongoing conference via the real-time voting interface;

determine, based on a voting rule, whether the respective votes indicate to transmit the notification; and

in response to determining that the respective votes indicate to transmit the notification, transmit the notification indicative of the topic-of-interest and the ongoing conference to the user.

9 . The device of claim 8 , wherein to transmit the notification indicative of the topic-of-interest and the ongoing conference comprises to:

obtain, from another participant, a confirmation to send the notification; and

transmit the confirmation to the user in response to receiving the confirmation.

10 . The device of claim 8 , wherein to generate the real-time transcript comprises to:

obtain a portion of a speech from a device associated with another participant and connected to the ongoing conference;

identify, in the portion of the speech, the another participant as a first speaker;

identify, in the portion of the speech, at least one second speaker other than the another participant; and

in response to determining that a signal associated with the speech of the another participant has a highest quality amongst the signal associated with the speech of the another participant and an at least one signal associated with the at least one second speaker, generate the real-time transcript based on the speech of the another participant and disregarding the speech of the at least one second speaker.

11 . The device of claim 8 , wherein the notification includes conference joining details.

12 . The device of claim 8 , wherein the processor is further configured to execute instructions stored in the memory to:

receive, from another participant, an indication to disable a transcription of speech of the another participant, wherein the indication to disable the transcription is such that while the transcription is disabled, other participants are able to hear the another participant but no transcription is obtained of the speech of the another participant.

13 . The device of claim 8 , wherein the processor is further configured to execute instructions stored in the memory to:

receive a message from the user; and

present the message to participants of the ongoing conference without joining the user to the ongoing conference.

14 . A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:

generating, using a transcription engine accessing audio of an ongoing conference implemented by a conferencing software and including participants, a real-time transcript of a portion of the ongoing conference, wherein generating the real-time transcript comprises:

determining that audio accessed by the transcription engine includes speech from a person who is not a participant of the ongoing conference, wherein the speech from the person is included in audio data associated with one of the participants; and

in response to determining that the audio accessed by the transcription engine includes the speech from the person who is not a participant of the ongoing conference, preventing the speech from the person from being included in the real-time transcript; and

responsive to detecting that a topic-of-interest associated with a user who is not a current participant of the ongoing conference is referenced within the real-time transcript:

presenting, via the conferencing software, a real-time voting interface to at least some participants of the ongoing conference;

identifying respective votes of at least some of the participants of the ongoing conference, wherein each of the respective votes indicates whether a notification indicative of the topic-of-interest is to be transmitted to the user responsive to detecting that the topic-of-interest is associated with the user, wherein each of the respective votes indicates whether a notification indicative of the topic-of-interest is to be transmitted to the user responsive to detecting that the topic-of-interest is associated with the user, and wherein the respective votes are collected in real-time from the participants of the ongoing conference via the real-time voting interface;

determining, based on a voting rule, whether the respective votes indicate to transmit the notification; and

in response to determining that the respective votes indicate to transmit the notification, transmitting the notification indicative of the topic-of-interest and the ongoing conference to the user.

15 . The non-transitory computer readable medium of claim 14 , wherein the operations further comprise:

receiving from another participant of the ongoing conference a command to send a request to another user to join the ongoing conference; and

sending the request to the another user to join the ongoing conference.

16 . The non-transitory computer readable medium of claim 14 , wherein the operations further comprise:

receiving from another participant a command to schedule a meeting for a subset of current participants of the ongoing conference, wherein the command includes the subset of the current participants; and

sending a request to a calendaring software to schedule the meeting.

17 . The non-transitory computer readable medium of claim 14 , wherein the operations further comprise:

receiving, from another participant, an indication to disable transcription of speech of the another participant, wherein the indication to disable a transcription is such that while the transcription is disabled, other participants are able to hear the another participant but no transcription is obtained of the speech of the another participant.

18 . The non-transitory computer readable medium of claim 14 , wherein the operations further comprise:

receiving a message from the user; and

presenting the message to participants of the ongoing conference without joining the user to the ongoing conference.

19 . The non-transitory computer readable medium of claim 14 , wherein the operations further comprise:

receiving the respective votes from at least some users that meet joining criteria of the ongoing conference.

20 . The non-transitory computer readable medium of claim 14 , wherein the operations further comprise:

identifying another user based on the real-time transcript, wherein the another user is not a current participant of the ongoing conference; and

determining whether to send a notification to the another user based on a response received from another participant of the ongoing conference to a prompt to confirm that the notification is to be sent to the another user.

Assignments (2)

Continuity (1)

References Cited (26)