公开(公告)号：US20230206895A1

公开(公告)日：2023-06-29

申请号：US18089576

申请日：2022-12-28

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Wan Ding ,  Dongyan Huang ,  Zhiyuan Zhao ,  Zhiyong Yang

IPC: G10L13/047 ,  G10L13/10

CPC classification number: G10L13/047 ,  G10L13/10

Abstract: A speech synthesis method includes: obtaining an acoustic feature sequence of a text to be processed; processing the acoustic feature sequence by using a non-autoregressive computing model in parallel to obtain first audio information of the text, to be processed, wherein the first audio information comprises audio corresponding to each segment; processing the acoustic feature sequence and the first audio information by using an autoregressive computing model to obtain a residual value corresponding to each segment; and obtaining second audio information corresponding to an i-th segment based on the first audio information corresponding to the i-th segment and the residual values corresponding to a first to an (i-1)-th segment, wherein a synthesized audio of the text to be processed comprises each of the second audio information, i=1, 2 . . . n, n is a total number of the segments.

公开(公告)号：US20210193160A1

公开(公告)日：2021-06-24

申请号：US17084672

申请日：2020-10-30

Applicant: UBTECH ROBOTICS CORP LTD.

Inventor： RUOTONG WANG ,  Zhichao Tang ,  Dongyan Huang ,  Jiebin Xie ,  Zhiyuan Zhao ,  Yang Liu ,  Youjun Xiong

IPC: G10L21/013 ,  G10L25/03 ,  G10L25/27 ,  G10L19/02 ,  G06N20/00

Abstract: The present disclosure discloses a voice conversion method. The method includes: obtaining a to-be-converted voice, and extracting acoustic features of the to-be-converted voice; obtaining a source vector corresponding to the to-be-converted voice from a source vector pool, and selecting a target vector corresponding to the target voice from the target vector pool; obtaining acoustic features of the target voice output by the voice conversion model by using the acoustic features of the to-be-converted voice, the source vector corresponding to the to-be-converted voice, and the target vector corresponding to the target voice as an input of the voice conversion model; and obtaining the target voice by converting the acoustic features of the target voice using a vocoder. In addition, a voice conversion apparatus and a storage medium are also provided.

公开(公告)号：US11996112B2

公开(公告)日：2024-05-28

申请号：US17084672

申请日：2020-10-30

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Ruotong Wang ,  Zhichao Tang ,  Dongyan Huang ,  Jiebin Xie ,  Zhiyuan Zhao ,  Yang Liu ,  Youjun Xiong

IPC: G10L25/21 ,  G06N20/00 ,  G10L19/02 ,  G10L21/013 ,  G10L25/03 ,  G10L25/24 ,  G10L25/27 ,  G10L25/75

CPC classification number: G10L21/013 ,  G06N20/00 ,  G10L19/02 ,  G10L25/03 ,  G10L25/27 ,  G10L2021/0135

Abstract: The present disclosure discloses a voice conversion method. The method includes: obtaining a to-be-converted voice, and extracting acoustic features of the to-be-converted voice; obtaining a source vector corresponding to the to-be-converted voice from a source vector pool, and selecting a target vector corresponding to the target voice from the target vector pool; obtaining acoustic features of the target voice output by the voice conversion model by using the acoustic features of the to-be-converted voice, the source vector corresponding to the to-be-converted voice, and the target vector corresponding to the target voice as an input of the voice conversion model; and obtaining the target voice by converting the acoustic features of the target voice using a vocoder. In addition, a voice conversion apparatus and a storage medium are also provided.