US 12,475,892 B2
Talking speed analysis per topic segment in a communication session
Vijay Parthasarathy, San Jose, CA (US); Xiaoli Song, Redding, CA (US); Yaling Song, Hangzhou (CN); Shaoyang Wu, Hangzhou (CN); and Min Xiao-Devins, San Jose, CA (US)
Assigned to Zoom Communications, Inc., San Jose, CA (US)
Filed by Zoom Communications, Inc., San Jose, CA (US)
Filed on Jan. 31, 2022, as Appl. No. 17/589,832.
Claims priority of application No. 202220158736.1 (CN), filed on Jan. 20, 2022.
Prior Publication US 2023/0230596 A1, Jul. 20, 2023
Int. Cl. G10L 15/26 (2006.01); G10L 15/06 (2013.01); G10L 15/22 (2006.01); H04L 12/18 (2006.01)
CPC G10L 15/26 (2013.01) [G10L 15/063 (2013.01); G10L 15/22 (2013.01); H04L 12/1822 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
connecting to a communication session with a plurality of participants;
receiving a transcript of a conversation between the participants produced during the communication session, the transcript comprising timestamps for each utterance of a speaking participant;
detecting one or more filler words in the transcript;
determining that one or more of the filler words is a false positive filler word;
removing the false positive filler word from the one or more filler words to obtain filtered filler words;
classifying the filtered filler words into filler types from a predetermined list of filler types;
highlighting the filtered filler words in the transcript;
determining a talking speed of the speaking participant based on an analysis of the transcript;
determining a meeting type for the communication session; based on the analysis of the transcript;
generating, based on the meeting type, a plurality of topic segments for the conversation and respective timestamps for the topic segments;
for each topic segment, determining, based on analysis of the transcript and the timestamps for each utterance in the topic segment, a word count per unit of time for each speaking participant associated with a prespecified organization; and
presenting, to one or more client devices, data relating to the word count per unit of time for speaking participants (a) according to each topic segment of the communication session, (b) for all topic segments of the communication session, (c) according to each topic segment across multiple communication sessions, (d) for multiple topic segments of multiple communication sessions sharing the meeting type, and (e) aggregated across an entire team for each topic segment, across multiple topic segments of multiple communication sessions sharing the meeting type, and across multiple topic segments of multiple communication sessions having varying meeting types.