公开(公告)号：US20240169998A1

公开(公告)日：2024-05-23

申请号：US18423990

申请日：2024-01-26

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xianbo Meng ,  Bingyin Xia ,  Zhe Wang

IPC: G10L19/008 ,  G10L19/022

CPC classification number: G10L19/008 ,  G10L19/022

Abstract: In a multi-channel signal encoding method, a current frame includes a first sound channel and a second sound channel. First group information of M blocks of the first sound channel and second group information of M blocks of the second sound channel are obtained. When the first group information and the second group information meet a preset condition, first adjusted group information and second adjusted group information are obtained based on the first group information and the second group information. Then, a first to-be-encoded spectrum is obtained based on the first adjusted group information and the spectrums of the M blocks of the first sound channel. Similarly, a second to-be-encoded spectrum may be obtained. Finally, the first to-be-encoded spectrum and the second to-be-encoded spectrum are encoded by using an encoding neural network to obtain a spectrum encoding result. The spectrum encoding result may be carried by a bitstream.