公开(公告)号：US20230199369A1

公开(公告)日：2023-06-22

申请号：US18173625

申请日：2023-02-23

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhipeng CHEN ,  Jiang LI ,  Shiqiang PENG ,  Xiangyu ZHAO ,  Fan FAN ,  Haiting LI ,  Tizheng WANG

IPC: H04R1/26 ,  H04R1/28

CPC classification number: H04R1/26 ,  H04R1/2834

Abstract: Embodiments of this application provide an audio data processing method and apparatus, and a sound box system, which are related to the field of audio technologies, and improve sound quality of an audio playing device. The sound box system includes a full-frequency sound box and a low-frequency sound box. The full-frequency sound box is physically connected to the low-frequency sound box by using a first fastening part of the full-frequency sound box and a second fastening part of the low-frequency sound box. Furthermore, the full-frequency sound box communicates with the low-frequency sound box by using a first communication part of the first fastening part and a second communication part of the second fastening part, where the first fastening part and the second fastening part are a group of paired connection parts, and the first communication part and the second communication part are a group of paired communication parts.

公开(公告)号：US20240096343A1

公开(公告)日：2024-03-21

申请号：US18522743

申请日：2023-11-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Shanyi WEI ,  Chao WU ,  Yan QIU ,  Meng LIAO ,  Fan FAN ,  Shiqiang PENG ,  Bin LI ,  Wenbin ZHAO ,  Jiang LI ,  Haiting LI ,  Xueyan HUANG

IPC: G10L21/0232 ,  G10L21/0308

CPC classification number: G10L21/0232 ,  G10L21/0308

Abstract: This application relates to the artificial intelligence (AI) field, and specifically, to a voice quality enhancement method and a related device. The method includes: after a PNR mode is enabled, obtaining a noisy voice signal and target voice-related data, where the noisy-carrying voice signal includes a voice signal of a target user and an interfering noise signal, and the target voice-related data indicates a voice feature of the target user; and performing noise reduction on the noisy voice signal based on the target voice-related data by using a trained voice noise reduction model to obtain a noise-reduced voice signal of the target user, where the voice noise reduction model is implemented based on a neural network. In embodiments of this application, voice of a target person can be enhanced, and interference can be suppressed.