公开(公告)号：US20230040515A1

公开(公告)日：2023-02-09

申请号：US17969454

申请日：2022-10-19

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Bingyin Xia ,  Jiawei Li ,  Zhe Wang

IPC: G10L19/02 ,  G10L19/22

Abstract: An audio signal coding method is provided that includes: obtaining a current frame of an audio signal; obtaining a coding parameter based on a power spectrum ratio of a current frequency in a current frequency area of at least a part of signals of the current frame, where the coding parameter indicates tonal component information of the at least a part of signals, the tonal component information includes at least one of location information of a tonal component, quantity information of tonal components, amplitude information of the tonal component, or energy information of the tonal component, and the power spectrum ratio of the current frequency is a ratio of a value of a power spectrum of the current frequency to a mean value of power spectrums of the current frequency area; and performing bitstream multiplexing on the coding parameter to obtain a coded bitstream.

公开(公告)号：US20220375213A1

公开(公告)日：2022-11-24

申请号：US17880318

申请日：2022-08-03

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hang Xu ,  Zhili Liu ,  Fengwei Zhou ,  Jiawei Li ,  Xiaodan Liang ,  Zhenguo Li ,  Li Qian

IPC: G06V10/82 ,  G06V10/77 ,  G06N3/063 ,  G06V10/28 ,  G06V10/774

Abstract: A processing apparatus includes a collection module and a training module, the training module includes a backbone network and a region proposal network (RPN) layer, the backbone network is connected to the RPN layer, and the RPN layer includes a class activation map (CAM) unit. The collection module is configured to obtain an image, where the image includes an image with an instance-level label and an image with an image-level label. The backbone network is used to output a feature map of the image based on the image obtained by the collection module.