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:
Jun. 29, 2021

Filed:

Apr. 25, 2019
Applicant:

Electronic Arts Inc., Redwood City, CA (US);

Inventors:

Jorge del Val Santos, Stockholm, SE;

Linus Gisslén, Solna, SE;

Martin Singh-Blom, Stockholm, SE;

Kristoffer Sjöö, Stockholm, SE;

Mattias Teye, Sundbyberg, SE;

Assignee:

ELECTRONIC ARTS INC., Redwood City, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 13/20 (2011.01); G06N 3/08 (2006.01); G06N 20/20 (2019.01); G06T 13/40 (2011.01);
U.S. Cl.
CPC ...
G06T 13/205 (2013.01); G06N 3/088 (2013.01); G06N 20/20 (2019.01); G06T 13/40 (2013.01);
Abstract

A computer-implemented method for generating a machine-learned model to generate facial position data based on audio data comprising training a conditional variational autoencoder having an encoder and decoder. The training comprises receiving a set of training data items, each training data item comprising a facial position descriptor and an audio descriptor; processing one or more of the training data items using the encoder to obtain distribution parameters; sampling a latent vector from a latent space distribution based on the distribution parameters; processing the latent vector and the audio descriptor using the decoder to obtain a facial position output; calculating a loss value based at least in part on a comparison of the facial position output and the facial position descriptor of at least one of the one or more training data items; and updating parameters of the conditional variational autoencoder based at least in part on the calculated loss value.


Find Patent Forward Citations

Loading…