Title:
SPEECH SYNTHESIS METHOD AND APPARATUS, COMPUTER DEVICE AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/004113
Kind Code:
A1
Abstract:
Provided are a speech synthesis method and apparatus, a computer device and a storage medium. The method comprises: acquiring a facial picture in a video to be dubbed (S10); extracting facial features of the facial picture (S20); determining, according to the facial features, a facial label corresponding to the facial picture in the video to be dubbed (S30); selecting, from an acoustic model library, an acoustic model corresponding to the facial label, wherein the acoustic model comprises a plurality of speech labels (S40); determining speech feature parameters corresponding to each speech label in the plurality of speech labels (S50); and synthesizing, by using the speech feature parameters corresponding to each speech label, speech for a character corresponding to the facial picture in the video to be dubbed (S60), so that the aim of improving the dubbing accuracy rate is realized.
Inventors:
XIANG CHUNYU (CN)
Application Number:
PCT/CN2020/085572
Publication Date:
January 14, 2021
Filing Date:
April 20, 2020
Export Citation:
Assignee:
ONE CONNECT SMART TECH CO LTD SHENZHEN (CN)
International Classes:
G06K9/00; G10L13/02; G10L13/08
Foreign References:
| CN110459200A | 2019-11-15 | |||
| CN106531148A | 2017-03-22 | |||
| CN106575500A | 2017-04-19 | |||
| CN105931631A | 2016-09-07 | |||
| CN107507620A | 2017-12-22 | |||
| US6839672B1 | 2005-01-04 | |||
| US20060204060A1 | 2006-09-14 |
Attorney, Agent or Firm:
SHENZHEN ZHONGDING INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF: