Patent · US Active

Voice generation for virtual characters

US12412559B2 · kind B2 · utility

0Cited by
2References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 23, 2022
Grant dateSep 9, 2025
Priority date
Expiry dateNov 1, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L21/003
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present disclosure describes techniques of generating voices for virtual characters. A plurality of source sounds may be received. The plurality of source sounds may correspond to a plurality of frames of a video. The video may comprise a virtual character. The plurality of source sounds may be converted into a plurality of representations in a latent space using a first model. Each representation among the plurality of representations may comprise a plurality of parameters. The plurality of parameters may correspond to a plurality of sound features. A plurality of sounds may be generated in real time for the virtual character in the video based at least in part on modifying at least one of the plurality of parameters of each representation.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.