US 12,406,669 B2
Method, apparatus, and computer program product for searchable real-time transcribed audio and visual content within a group-based communication system
Andrew Locascio, San Francisco, CA (US); Lynsey Haynes, San Francisco, CA (US); Jahanzeb Sherwani, San Francisco, CA (US); and Jason Dicioccio, Santa Clara, CA (US)
Assigned to Salesforce, Inc., San Francisco, CA (US)
Filed by Salesforce, Inc., San Francisco, CA (US)
Filed on Jul. 14, 2023, as Appl. No. 18/352,930.
Application 18/352,930 is a continuation of application No. 17/175,189, filed on Feb. 12, 2021, granted, now 11,769,498.
Application 17/175,189 is a continuation of application No. 16/101,130, filed on Aug. 10, 2018, granted, now 10,923,121, issued on Feb. 16, 2021.
Claims priority of provisional application 62/544,204, filed on Aug. 11, 2017.
Prior Publication US 2023/0377575 A1, Nov. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/26 (2006.01); G06F 16/683 (2019.01); G06V 40/16 (2022.01); G10L 15/18 (2013.01); G10L 15/22 (2006.01); G10L 15/30 (2013.01); H04L 12/18 (2006.01); H04L 51/066 (2022.01); H04N 7/15 (2006.01)
CPC G10L 15/22 (2013.01) [G06F 16/685 (2019.01); G06V 40/161 (2022.01); G06V 40/172 (2022.01); G10L 15/1822 (2013.01); G10L 15/26 (2013.01); G10L 15/30 (2013.01); H04L 12/1831 (2013.01); H04L 51/066 (2013.01); H04L 12/1822 (2013.01); H04M 2203/50 (2013.01); H04N 7/15 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method comprising:
receiving, from a secure group of users that are members of a channel associated with a channel name, messaging communications, wherein the channel is a virtual communications environment or feed that is configured to display, to users of the secure group of users on one or more client devices and via a user interface associated with the channel, the messaging communications posted by channel members and a visual depiction of an option to start a channel meeting;
receiving audio from the channel meeting comprising a plurality of speakers from the secure group of users, the audio comprising spoken text received from a respective speaker of the plurality of speakers participating in the channel meeting, wherein the channel meeting is started from the channel via a user selection of the visual depiction of the option to start the channel meeting;
converting the spoken text into a live transcription using a model;
assembling the live transcription into a written record that is associated with the channel name, a speaker attribution, and a meeting name, wherein the channel name, the speaker attribution, and the meeting name associate the audio with the plurality of speakers;
causing display, at the channel and to the plurality of speakers while the channel meeting is occurring, of the messaging communications and a transcript interface comprising the live transcription so that the live transcription is simultaneously displayed in real-time to each of the respective speakers;
storing the written record as a searchable transcript in the channel, wherein the searchable transcript associates the live transcription with the channel using the channel name; and
retrieving the searchable transcript from the channel after the channel meeting based at least in part on storing the written record.