US 12,477,070 B1
Machine-learning assisted acoustic echo cancelation
Yuhui Chen, San Jose, CA (US); Zhaofeng Jia, Saratoga, CA (US); and Wei Wang, Hefei (CN)
Assigned to Zoom Communications, Inc., San Jose, CA (US)
Filed by Zoom Video Communications, Inc., San Jose, CA (US)
Filed on Nov. 2, 2023, as Appl. No. 18/386,298.
Int. Cl. H04M 9/08 (2006.01); G10L 21/0208 (2013.01); G10L 25/30 (2013.01)
CPC H04M 9/082 (2013.01) [G10L 21/0208 (2013.01); G10L 25/30 (2013.01); G10L 2021/02082 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing an audio signal;
identifying, using a trained, machine-learning (“ML”) model, the audio signal as a unitary voice signal;
applying a first mode of acoustic echo cancelation (AEC) to an audio frame of the unitary voice signal to produce a test frame;
measuring a residual echo in the test frame to produce a residual value;
comparing the residual value to a threshold; and
applying a second mode of AEC to the audio signal based on the comparing.