System and method for synthesizing photo-realistic video of a speech
C Pan, W Liu, L Yi - US Patent 11,682,153, 2023 - Google Patents
2020-09-12 Assigned to JD FINANCE AMERICA CORPORATION, JINGDONG DIGITS
TECHNOLOGY HOLDING CO., LTD. reassignment JD FINANCE AMERICA CORPORATION …
TECHNOLOGY HOLDING CO., LTD. reassignment JD FINANCE AMERICA CORPORATION …
Method for outputting blend shape value, storage medium, and electronic device
H Sima, T Cuicui, L Zheng - US Patent 11,847,726, 2023 - Google Patents
A method for outputting a blend shape value includes: performing feature extraction on
obtained target audio data to obtain a target audio feature vector; inputting the target audio …
obtained target audio data to obtain a target audio feature vector; inputting the target audio …
Visual speech recognition based on connectionist temporal classification loss
S Jin, JH Lee, M Wnuk, F Costela - US Patent App. 17/689,270, 2023 - Google Patents
Various embodiments of the disclosure relate to speech recognition and deep neural
networks. More specifically, various embodiments of the disclosure relate to an electronic …
networks. More specifically, various embodiments of the disclosure relate to an electronic …
Method for audio-driven character lip sync, model for audio-driven character lip sync and training method therefor
H Sima, L Zheng - US Patent 11,928,767, 2024 - Google Patents
Embodiments of the present disclosure provide a method for audio-driven character lip sync,
a model for audio-driven character lip sync, and a training method therefor. A target dynamic …
a model for audio-driven character lip sync, and a training method therefor. A target dynamic …