US 12,073,847 B2
System and method for acoustic echo cancelation using deep multitask recurrent neural networks
Amin Fazeli, San Diego, CA (US); Mostafa El-Khamy, San Diego, CA (US); and Jungwon Lee, San Diego, CA (US)
Assigned to Samsung Electronics Co., Ltd., Yongin-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on May 27, 2022, as Appl. No. 17/827,424.
Application 17/827,424 is a continuation of application No. 16/751,094, filed on Jan. 23, 2020, granted, now 11,393,487.
Application 16/751,094 is a continuation in part of application No. 16/573,573, filed on Sep. 17, 2019, granted, now 10,803,881, issued on Oct. 13, 2020.
Claims priority of provisional application 62/914,875, filed on Oct. 14, 2019.
Claims priority of provisional application 62/838,146, filed on Apr. 24, 2019.
Claims priority of provisional application 62/825,681, filed on Mar. 28, 2019.
Prior Publication US 2022/0293120 A1, Sep. 15, 2022
Int. Cl. G10L 21/0232 (2013.01); G06N 3/08 (2023.01); G06N 20/10 (2019.01); G10L 21/0208 (2013.01); H04R 3/04 (2006.01)
CPC G10L 21/0232 (2013.01) [G06N 3/08 (2013.01); G06N 20/10 (2019.01); H04R 3/04 (2013.01); G10L 2021/02082 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to:
receive a far-end signal and a near-end signal comprising at least an echo signal corresponding to the far-end signal;
generate, by a contextual-attention neural network, a plurality of estimated near-end features based at least in part on the received near-end signal and the received far-end signal, without using an estimated echo signal; and
generate, based on the plurality of estimated near-end features, an estimated near-end signal, the estimated near-end signal corresponding to the near-end signal without the echo signal.