公开(公告)号：US12142274B2

公开(公告)日：2024-11-12

申请号：US17607390

申请日：2020-05-15

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Shuwei Li ,  Xiang Chen

IPC: G10L15/22 ,  G10L15/08 ,  G10L21/0216

Abstract: A voice wakeup method and a device are provided. The method includes: receiving, by a third-party device, wakeup messages sent by at least two electronic devices, where the wakeup message includes wakeup keyword energy information used to indicate a wakeup keyword energy value, and the wakeup keyword energy value; normalizing wakeup keyword energy values based on ambient sound energy and/or sound collection capabilities of devices, to obtain at least two normalized wakeup keyword energy values; and based on the at least two normalized wakeup keyword energy values, sending a wakeup permission instruction to a first electronic device in the at least two electronic devices, and sending a wakeup prohibition instruction to another electronic device other than the first electronic device, where a normalized wakeup keyword energy value of the first electronic device is a maximum value. This helps improve accuracy of waking up a device nearby in a multi-device scenario.

公开(公告)号：US12130899B2

公开(公告)日：2024-10-29

申请号：US17587904

申请日：2022-01-28

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yuan Sun ,  Shuwei Li ,  Youyu Jiang ,  Shen Qu ,  Ming Kuang

IPC: H04L9/00 ,  G06F21/32 ,  G10L17/22

CPC classification number: G06F21/32 ,  G10L17/22

Abstract: This application provides a voiceprint recognition method and device. The method includes: calculating, by an electronic device a first confidence value that an entered voice belongs to a first registered user, and calculating a second confidence value that the entered voice belongs to a second registered user. The method further includes: calculating, by another electronic device, a third confidence value that the entered voice belongs to the first registered user, and calculating a fourth confidence value that the entered voice belongs to the second registered user. A server determines, based on the first confidence value and the third confidence value, a fifth confidence value that a user is the first registered user, and determines, based on the second confidence value and the fourth confidence value, a sixth confidence value that the user is the second registered user.

公开(公告)号：US20220223150A1

公开(公告)日：2022-07-14

申请号：US17607390

申请日：2020-05-15

Applicant: HUAWEI TECHNOLOGIES CO.,LTD.

Inventor： Shuwei Li ,  Xiang Chen

IPC: G10L15/22 ,  G10L15/08

Abstract: A voice wakeup method and a device are provided. The method includes: receiving, by a third-party device, wakeup messages sent by at least two electronic devices, where the wakeup message includes wakeup keyword energy information used to indicate a wakeup keyword energy value, and the wakeup keyword energy value; normalizing wakeup keyword energy values based on ambient sound energy and/or sound collection capabilities of devices, to obtain at least two normalized wakeup keyword energy values; and based on the at least two normalized wakeup keyword energy values, sending a wakeup permission instruction to a first electronic device in the at least two electronic devices, and sending a wakeup prohibition instruction to another electronic device other than the first electronic device, where a normalized wakeup keyword energy value of the first electronic device is a maximum value. This helps improve accuracy of waking up a device nearby in a multi-device scenario.