US 12,293,769 B2
Neural-echo: an unified deep neural network model for acoustic echo cancellation and residual echo suppression
Meng Yu, Palo Alto, CA (US); and Dong Yu, Palo Alto, CA (US)
Assigned to TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed by TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed on Aug. 21, 2023, as Appl. No. 18/452,992.
Application 18/452,992 is a continuation of application No. 17/485,943, filed on Sep. 27, 2021, granted, now 11,776,556.
Prior Publication US 2023/0395091 A1, Dec. 7, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 21/0224 (2013.01); G06N 3/02 (2006.01); H04R 3/04 (2006.01); G10L 21/0208 (2013.01); G10L 21/0216 (2013.01)
CPC G10L 21/0224 (2013.01) [G06N 3/02 (2013.01); H04R 3/04 (2013.01); G10L 2021/02082 (2013.01); G10L 2021/02163 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of acoustic echo suppression, executable by a processor, comprising:
receiving a microphone signal and a far-end reference signal;
estimating an echo signal based on multi-tap filtering of the far-end reference signal;
generating an echo cancelled signal based on subtracting the estimated echo signal from the microphone signal; and
outputting a near-end speech signal based on the echo cancelled signal, the microphone signal, and the far-end reference signal.