公开(公告)号：US10909989B2

公开(公告)日：2021-02-02

申请号：US16213421

申请日：2018-12-07

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Wei Li ,  Binghua Qian ,  Xingming Jin ,  Ke Li ,  Fuzhang Wu ,  Yongjian Wu ,  Feiyue Huang

IPC: G10L15/00 ,  G10L15/02 ,  G10L17/02 ,  G10L17/14 ,  G10L17/20

Abstract: An identity vector generation method is provided. The method includes obtaining to-be-processed speech data. Corresponding acoustic features are extracted from the to-be-processed speech data. A posterior probability that each of the acoustic features belongs to each Gaussian distribution component in a speaker background model is calculated to obtain a statistic. The statistic is mapped to a statistic space to obtain a reference statistic, the statistic space built according to a statistic corresponding to a speech sample exceeding a threshold speech duration. A corrected statistic is determined according to the calculated statistic and the reference statistic; and an identity vector is generated according to the corrected statistic.