Jose J Valle

US Patent:

20230035306, Feb 2, 2023

Filed:

Jul 21, 2021

Appl. No.:

17/382027

Inventors:

- Santa Clara CA, US
Koki Nagano - Playa Vista CA, US
Yeongho Seol - Seoul, KR
Jose Rafael Valle Gomes da Costa - Sunnyvale CA, US
Jaewoo Seo - Kirkland WA, US
Ting-Chun Wang - Santa Clara CA, US
Arun Mallya - Mountain View CA, US
Sameh Khamis - Alameda CA, US
Wei Ping - Sunnyvale CA, US
Rohan Badlani - San Jose CA, US
Kevin Jonathan Shih - Santa Clara CA, US
Bryan Catanzaro - Los Altos Hills CA, US
Simon Yuen - Playa Vista CA, US
Jan Kautz - Lexington MA, US

International Classification:

G06T 13/40
H04N 19/597
G06N 3/04
G10L 13/04
G06T 9/00
G06T 17/10
G06T 13/20

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