-
公开(公告)号:US20230377556A1
公开(公告)日:2023-11-23
申请号:US17751324
申请日:2022-05-23
Applicant: Lemon Inc.
Inventor: Zeng Dai , Chen Sun , Ari Shapiro , Kin Chung Wong , Weishan Yu , August Yadon
CPC classification number: G10L13/02 , G06T13/40 , G06T13/205
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.