公开(公告)号：US10916249B2

公开(公告)日：2021-02-09

申请号：US16265237

申请日：2019-02-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngho Han ,  Keunseok Cho ,  Jaeyoung Roh ,  Namhoon Kim ,  Chiyoun Park ,  Jongyoub Ryu

IPC: G10L15/22 ,  G10L15/02 ,  G10L15/187 ,  G10L25/84 ,  G10L17/02 ,  G10L17/24

Abstract: A method of processing a speech signal for speaker recognition in an electronic apparatus includes: obtaining a speech signal of a first user; extracting a speech feature comprising a feature value from the speech signal; comparing the speech feature extracted from the speech signal of the first user with a predetermined reference value; selecting a first user feature that corresponds to the speech feature of the first user compared with the reference value; generating a recommended phrase used for speaker recognition based on the first user feature; and outputting the recommended phrase.