公开(公告)号：US12118989B2

公开(公告)日：2024-10-15

申请号：US17507437

申请日：2021-10-21

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xu Chen ,  Jinfeng Bai ,  Runqiang Han ,  Lei Jia

IPC: G10L15/20 ,  G06N3/084 ,  G10L15/06 ,  G10L15/22 ,  G10L21/0208 ,  G10L21/0232 ,  G10L21/038 ,  G10L25/30

CPC classification number: G10L15/20 ,  G06N3/084 ,  G10L15/063 ,  G10L15/22 ,  G10L21/0232 ,  G10L21/038 ,  G10L25/30 ,  G10L2021/02082

Abstract: The present disclosure provides a speech processing method, and a method for generating a speech processing model, related to a field of signal processing technologies. The speech processing method includes: obtaining M speech signals to be processed and N reference signals; performing sub-band decomposition on each of the M speech signals and each of the N reference signals to obtain frequency-band components in each speech signal and each reference signal; processing the frequency-band components in each speech signal and each reference signal by using an echo cancellation model, to obtain an ideal ratio mask corresponding to the N reference signals in each frequency band of each speech signal; and performing echo cancellation on each frequency-band component of each speech signal based on the ideal ratio mask corresponding to the N reference signals in each frequency band of each speech signal, to obtain M echo-cancelled speech signals.