公开(公告)号：US20220375453A1

公开(公告)日：2022-11-24

申请号：US17875529

申请日：2022-07-28

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Junteng Zhang ,  Jianmin Wu ,  Tao Sun ,  Lei Jia

IPC: G10L13/10 ,  G10L13/06 ,  G10L13/047 ,  G10L25/18 ,  G10L13/08

Abstract: A method for speech synthesis includes obtaining text to be synthesized and an identifier of a speaker, the text being written in a first language; obtaining pronunciation information of each character in the text; generating linguistic features of the text by performing feature extraction on the pronunciation information of each character in the text based on the first language; and obtaining a target speech in a second language other than the first language, by performing speech synthesis based on the linguistic features and the identifier of the speaker.