公开(公告)号：US11727912B1

公开(公告)日：2023-08-15

申请号：US17707125

申请日：2022-03-29

Applicant: Amazon Technologies, Inc.

Inventor： Harsha Inna Kedage Rao ,  Srivatsan Kandadai ,  Minje Kim ,  Tarun Pruthi ,  Trausti Thor Kristjansson

IPC: G10K11/178 ,  G10K11/175

CPC classification number: G10K11/17854 ,  G10K11/1754 ,  G10K11/17823 ,  G10K11/17825 ,  G10K11/17881 ,  G10K2210/3026 ,  G10K2210/3027 ,  G10K2210/3028 ,  G10K2210/3038 ,  G10K2210/505

Abstract: A system configured to perform deep adaptive acoustic echo cancellation (AEC) to improve audio processing. Due to mechanical noise and continuous echo path changes caused by movement of a device, echo signals are nonlinear and time-varying and not fully canceled by linear AEC processing alone. To improve echo cancellation, deep adaptive AEC processing integrates a deep neural network (DNN) and linear adaptive filtering to perform echo and/or noise removal. The DNN is configured to generate a nonlinear reference signal and step-size data, which the linear adaptive filtering uses to generate output audio data representing local speech. The DNN may generate the nonlinear reference signal by generating mask data that is applied to a microphone signal, such that the reference signal corresponds to a portion of the microphone signal that does not include near-end speech.