Title:
APPARATUS AND METHOD FOR GENERATING SYNTHESIZED SPPECH IMAGE
Document Type and Number:
WIPO Patent Application WO/2023/153553
Kind Code:
A1
Abstract:
Disclosed are an apparatus and method for generating a synthesized speech image. The apparatus for generating a synthesized speech image, according to an embodiment, is a machine learning-based apparatus for generating a synthesized speech image, comprising: a first global geometric transformation prediction unit that receives an input of each of a source image and a target image, which include the same person, and is trained to predict global geometric transformation for global movement of the person between the source image and the target image on the basis of the source image and the target image; a local feature tensor prediction unit that is trained to predict a feature tensor for local movement of the person on the basis of preconfigured input image; and an image generation unit that is trained to reconstruct the target image on the basis of the global geometric transformation, the source image, and the feature tensor for the local movement.
Inventors:
CHAE GYEONG SU (KR)
HWANG GUEM BUEL (KR)
HWANG GUEM BUEL (KR)
Application Number:
PCT/KR2022/003607
Publication Date:
August 17, 2023
Filing Date:
March 15, 2022
Export Citation:
Assignee:
DEEPBRAIN AI INC (KR)
International Classes:
G10L21/10; G06N20/00; G06T5/00; G06T7/269; G06T13/20; G10L15/04; G10L21/055
Domestic Patent References:
| WO2002031772A2 | 2002-04-18 |
Foreign References:
| US20200342634A1 | 2020-10-29 | |||
| KR20160041570A | 2016-04-18 | |||
| CN111797682A | 2020-10-20 |
Other References:
M. WANG; D. BRADLEY; S. ZAFEIRIOU; T. BEELER: "Facial Expression Synthesis using a Global‐Local Multilinear Framework", COMPUTER GRAPHICS FORUM : JOURNAL OF THE EUROPEAN ASSOCIATION FOR COMPUTER GRAPHICS, WILEY-BLACKWELL, OXFORD, vol. 39, no. 2, 13 July 2020 (2020-07-13), Oxford , pages 235 - 245, XP071545877, ISSN: 0167-7055, DOI: 10.1111/cgf.13926
Attorney, Agent or Firm:
T&C IP LAW FIRM (KR)
Download PDF: