US 12,380,908 B2
Dynamic noise and speech removal
Jiachuan Deng, Singapore (SG); Cheng-Lun Hu, Singapore (SG); Zhaofeng Jia, Saratoga, CA (US); Qiyong Liu, Singapore (SG); and Qi Yang, Hangzhou (CN)
Assigned to Zoom Communications, Inc., San Jose, CA (US)
Filed by Zoom Video Communications, Inc., San Jose, CA (US)
Filed on Mar. 22, 2022, as Appl. No. 17/701,517.
Prior Publication US 2023/0282225 A1, Sep. 7, 2023
Int. Cl. G10L 21/0232 (2013.01); G06F 3/16 (2006.01); G10L 21/034 (2013.01); G10L 25/30 (2013.01); G10L 25/51 (2013.01); H04L 65/80 (2022.01)
CPC G10L 21/0232 (2013.01) [G06F 3/165 (2013.01); G10L 21/034 (2013.01); G10L 25/30 (2013.01); G10L 25/51 (2013.01); H04L 65/80 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
receiving an input audio from an audio capturing device, the input audio comprising
speech from a participant of an online conference;
determining a type of audio playback device of the online conference; and
routing the received input audio to a first or second noise removal module, based on the determined type of the audio playback device, wherein:
the first noise removal module is configured to remove noise, the first noise removal module including a first artificial intelligence model trained to detect noise portions of the input audio; and
the second noise removal module is configured to remove noise and background speech, the second noise removal module including a second artificial intelligence model trained to detect noise portions of the input audio and background speech portions of the input audio.