US 11,688,384 B2
Noise management during an online conference session
Bjørn Winsvold, Tranby (NO); Eric Yi-hua Chen, Irvine, CA (US); Wei-Lien Hsu, Austin, TX (US); and Pi-Hsin Liu, Fremont, CA (US)
Assigned to CISCO TECHNOLOGY, INC., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Aug. 14, 2020, as Appl. No. 16/993,908.
Prior Publication US 2022/0051652 A1, Feb. 17, 2022
Int. Cl. G10K 11/178 (2006.01); H04L 12/18 (2006.01); G06N 20/00 (2019.01)
CPC G10K 11/17885 (2018.01) [G06N 20/00 (2019.01); H04L 12/1822 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining audio data from an endpoint participating in an online conference session, the audio data derived from audio captured at the endpoint that includes musical sounds;
processing the audio data to identify a portion of the audio data in which a decibel level of the musical sounds is stable for a period of time;
identifying non-musical noise present, if any, in the audio data with the musical sounds in response to identifying the portion of the audio data in which the decibel level of the musical sounds is stable for the period of time;
attenuating the non-musical noise from the audio data to generate noise-reduced musical audio data; and
transmitting the noise-reduced musical audio data for play out at one or more other endpoints participating in the online conference session.