US 11,863,711 B2
Speaker segment analysis for conferences
Tao Huang, Hangzhou (CN); Xiaoli Song, Sunnyvale, CA (US); Hui Wen, Hangzhou (CN); Melinda Min Xiao-Devins, Fremont, CA (US); Ran Yan, Hangzhou (CN); and Fangyi Zhao, Fremont, CA (US)
Assigned to Zoom Video Communications, Inc., San Jose, CA (US)
Filed by Zoom Video Communications, Inc., San Jose, CA (US)
Filed on Oct. 10, 2022, as Appl. No. 17/963,153.
Application 17/963,153 is a continuation of application No. 17/245,962, filed on Apr. 30, 2021, granted, now 11,570,403.
Application 17/245,962 is a continuation of application No. 17/245,988, filed on Apr. 30, 2021, granted, now 11,470,279.
Application 17/245,988 is a continuation of application No. 17/245,998, filed on Apr. 30, 2021.
Application 17/245,998 is a continuation of application No. 17/246,000, filed on Apr. 30, 2021, granted, now 11,616,658.
Prior Publication US 2023/0035155 A1, Feb. 2, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 7/15 (2006.01); G06F 40/166 (2020.01); G06F 40/289 (2020.01); G11B 27/031 (2006.01)
CPC H04N 7/155 (2013.01) [G06F 40/166 (2020.01); G06F 40/289 (2020.01); G11B 27/031 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining a transcript of a conference, wherein the transcript includes strings with respective timestamps and respective speaker identifiers;
identifying, using a processing apparatus, speaker segments with respective durations in the transcript, wherein a speaker segment is a sequence of consecutive strings in the transcript that have the same speaker identifier;
selecting a string based on a respective duration of the speaker segment in which the string occurs;
selecting a video excerpt from a video of the conference based on the respective timestamp of the selected string; and
generating a video conference summary as a sequence of video excerpts from the video, including the selected video excerpt.