Systems and methods for generating synthetic videos based on audio contents
US11968433B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Apr 15, 2022 |
| Grant date | Apr 23, 2024 |
| Priority date | — |
| Expiry date | Apr 15, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2021/105
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods for generating a synthetic video based on an audio are provided. An exemplary system may include a memory storing computer-readable instructions and at least one processor. The processor may execute the computer-readable instructions to perform operations. The operations may include receiving a reference video including a motion picture of a human face and receiving the audio including a speech. The operations may also include generating a synthetic motion picture of the human face based on the reference video and the audio. The synthetic motion picture of the human face may include a motion of a mouth of the human face presenting the speech. The motion of the mouth may match a content of the speech. The operations may further include generating the synthetic video based on the synthetic motion picture of the human face.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.