US 12,130,899 B2
Voiceprint recognition method and device
Yuan Sun, Xi'an (CN); Shuwei Li, Xi'an (CN); Youyu Jiang, Dongguan (CN); Shen Qu, Xi'an (CN); and Ming Kuang, Xi'an (CN)
Assigned to Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed by Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed on Jan. 28, 2022, as Appl. No. 17/587,904.
Application 17/587,904 is a continuation of application No. PCT/CN2020/103583, filed on Jul. 22, 2020.
Claims priority of application No. 201910688841.9 (CN), filed on Jul. 29, 2019.
Prior Publication US 2022/0229891 A1, Jul. 21, 2022
Int. Cl. H04L 9/00 (2022.01); G06F 21/32 (2013.01); G10L 17/22 (2013.01)
CPC G06F 21/32 (2013.01) [G10L 17/22 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A voiceprint recognition method, wherein a first electronic device comprises first voiceprint information of a first registered user and second voiceprint information of a second registered user, a second electronic device comprises third voiceprint information of the first registered user and fourth voiceprint information of the second registered user, wherein each of the first electronic device and the second electronic device includes a processor, a memory, and a sound pickup device, and the method comprises:
in response to a voice input of a user, receiving, by the sound pickup device of the first electronic device, a first voice entered by the user, and receiving, by the sound pickup device of the second electronic device, a second voice entered by the user;
determining, by the processor of the first electronic device based on the first voiceprint information, a first confidence value that the first voice belongs to the first registered user, and determining, based on the second voiceprint information, a second confidence value that the first voice belongs to the second registered user; and determining, by the processor of the second electronic device based on the third voiceprint information, a third confidence value that the second voice belongs to the first registered user, and determining, based on the fourth voiceprint information, a fourth confidence value that the second voice belongs to the second registered user;
sending, by the first electronic device, the first confidence value and the second confidence value to a server, and sending, by the second electronic device, the third confidence value and the fourth confidence value to the server, wherein the server includes a processor and a memory;
receiving, by the processor of the server, the first confidence value, the second confidence value, the third confidence value, and the fourth confidence value;
determining, by the processor of the server based on the first confidence value and the third confidence value, a fifth confidence value that the user is the first registered user, and determining, based on the second confidence value and the fourth confidence value, a sixth confidence value that the user is the second registered user; and
determining, by the processor of the server, that the user is the first registered user when the fifth confidence value is greater than the sixth confidence value, or determining, by the server, that the user is the second registered user when the sixth confidence value is greater than the fifth confidence value.