Invention Application
- Patent Title: SYNTHESIZING VIDEO FROM AUDIO USING ONE OR MORE NEURAL NETWORKS
-
Application No.: PCT/US2022/037852Application Date: 2022-07-21
-
Publication No.: WO2023004030A1Publication Date: 2023-01-26
- Inventor: LIU, Ming-Yu , NAGANO, Koki , SEOL, Yeongho , VALLE GOMES DA COSTA, Jose, Rafael , SEO, Jaewoo , WANG, Ting-Chun , MALLYA, Arun , KHAMIS, Sameh , PING, Wei , BADLANI, Rohan , SHIH, Kevin, Jonathan , CATANZARO, Bryan , YUEN, Simon , KAUTZ, Jan
- Applicant: NVIDIA CORPORATION
- Applicant Address: 2788 San Tomas Expressway
- Assignee: NVIDIA CORPORATION
- Current Assignee: NVIDIA CORPORATION
- Current Assignee Address: 2788 San Tomas Expressway
- Agency: ROSENTHAL, Gregory, B. et al.
- Priority: US17/382,027 2021-07-21
- Main IPC: G10L21/10
- IPC: G10L21/10 ; G06N3/02 ; G10L25/30
Abstract:
Apparatuses, systems, and techniques are presented to generate media content. In at least one embodiment, a first neural network is used to generate first video information based, at least in part, upon voice information corresponding to one or more users, and a second neural network is used to generate second video information corresponding to the one or more users based, at least in part, upon the first video information and one or more images corresponding to the one or more users.
Information query
