公开(公告)号：US20230081543A1

公开(公告)日：2023-03-16

申请号：US18057363

申请日：2022-11-21

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

Inventor： Bo Peng ,  Yongguo Kang ,  Cong Gao

IPC: G10L13/08 ,  G10L15/26 ,  G10L15/22 ,  G10L21/0232 ,  G10L25/18 ,  G10L13/047 ,  G10L15/02

Abstract: A method for synthetizing a speech includes: obtaining a source speech; suppressing a noise in the source speech based on an amplitude component and/or phase component of the source speech, to obtain a noise-reduced speech; performing a speech recognition process on the noise-reduced speech to obtain corresponding text information; inputting the text information of the noise-reduced speech and a preset tag into a trained acoustic model to obtain a predicted acoustic feature matching the text information; and generating a target speech based on the predicted acoustic feature.