AUDIO-DRIVEN FACIAL ANIMATION WITH ADAPTIVE SPEECH RATE

Number of patents in Portfolio can not be more than 2000

United States of America Patent

APP PUB NO 20250029307A1
SERIAL NO

18363455

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

In various examples, a technique for audio-driven facial animation with adaptive speech includes determining that a rate of speech associated with an audio segment exceeds a threshold. The technique also includes based at least on the rate of speech exceeding the threshold, upsampling a first set of features associated with the audio segment into a second set of features that is different in size than the first set of features. The technique further includes generating, using one or more machine learning models and based at least on at least a subset of the second set of features, a facial animation output corresponding to the audio segment.

First Claim

See full text

Other Claims data not available

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
NVIDIA CORPORATION2788 SAN TOMAS EXPRESSWAY SANTA CLARA CA 95051

International Classification(s)

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
HUANG, Zhengyu Shanghai, CN 26 45
KOROBCHENKO, Dmitry London, GB 6 0
LAI, Junjie Beijing, CN 4 0
LI, Tao Beijing, CN 743 4256
SEOL, Yeongho Seoul, KR 9 19
ZHANG, Rui Beijing, CN 806 5113
ZHANG, Weihua Beijing, CN 47 169
ZHONG, Yingying Shanghai, CN 7 3

Cited Art Landscape

Load Citation

Patent Citation Ranking

  • 0 Citation Count
  • G06T Class
  • 0 % this patent is cited more than
  • < 1 Age
Citation count rangeNumber of patents cited in rangeNumber of patents cited in various citation count ranges887101 - 10050100150200250300350400450500550600650700750800850900950

Forward Cite Landscape

Load Citation