The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jul. 29, 2025

Filed:

Jun. 07, 2023
Applicant:

Shanghai Lilith Technology Corporation, Shanghai, CN;

Inventors:

Huanhua Liao, Shanghai, CN;

Junfeng Li, Shanghai, CN;

Zhikai Li, Shanghai, CN;

Haonan Zhao, Shanghai, CN;

Xin Xiong, Shanghai, CN;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G10L 13/00 (2006.01); G10L 17/02 (2013.01); G10L 17/04 (2013.01); G10L 17/06 (2013.01); G10L 21/01 (2013.01); G10L 25/18 (2013.01);
U.S. Cl.
CPC ...
G10L 21/01 (2013.01); G10L 17/02 (2013.01); G10L 17/04 (2013.01); G10L 17/06 (2013.01); G10L 25/18 (2013.01);
Abstract

A voice conversion method used in an electronic device, including determining a target speech to be converted and a content representation vector corresponding to the target speech, where the target speech has a first content and a first voiceprint, and the content representation vector is obtained based on the speech waveform of the target speech; determining a reference speech and a voiceprint representation vector corresponding to the reference speech, where the reference speech has a second voiceprint, and the second voiceprint is different from the first voiceprint; generating a converted speech based on a speech generator according to the content representation vector and the voiceprint representation vector; where the converted speech has the first content and the second voiceprint; where the speech generator is obtained by jointly training a preset speech generation network and a preset discriminator network by using a training speech having the second voiceprint.


Find Patent Forward Citations

Loading…