Patent №
US 10,586,368
Granted
2020-03-10
Filed 2017
Owner
SNAP INC.
Lab
—
AI components
5
ml · nlp · vision · speech · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
15858992
The present invention relates to a joint automatic audio visual driven facial animation system that in some example embodiments includes a full scale state of the art Large Vocabulary Continuous Speech Recognition (LVCSR) with a strong language model for speech recognition and obtained phoneme alignment from the word lattice.
Machine learningNatural languageVisionSpeechAI hardwareG06T 13/205G06T 13/40G06V 20/64G06V 40/161G06V 40/171G06V 40/176G10L 21/10H04L 51/08+4 more
AI classification
Natural language1.00
Speech1.00
Machine learning1.00
Vision1.00
AI hardware0.95
Knowledge representation0.00
Planning0.00
Evolutionary computation0.00
Ownership
SNAP INC.
assignment · 516630056
Assignors
CAO, CHEN, CHEN, XIN, CHU, WEI, XUE, ZEHAO
On an employer assignment, the assignors are typically the inventors.
From the same owner
CHATBOT RESPONSE SYSTEMUS 12,695,713 · 2026AVATAR CALL PLATFORMUS 12,695,847 · 2026AR-BASED GUIDANCE FOR A USER OF A PERSONAL MOBILITY SYSTEMUS 12,679,492 · 2026N-FLOWS ESTIMATION FOR GARMENT TRANSFERUS 12,682,508 · 2026GESTURE-BASED SHARED AR SESSION CREATIONUS 12,675,169 · 2026ESTIMATING 3D SCENE REPRESENTATIONS OF IMAGESUS 12,675,908 · 2026VIDEO SYNTHESIS WITHIN A MESSAGING SYSTEMUS 12,670,362 · 2026CONTROLLING INTERACTIVE FASHION BASED ON BODY GESTURESUS 12,670,643 · 2026