公开(公告)号：US20250014589A1

公开(公告)日：2025-01-09

申请号：US18889390

申请日：2024-09-19

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yaoyuan Wang ,  Ziyang Zhang ,  Minglei Li ,  Weihua He ,  Yuhan Zhang ,  Haifeng Xing

IPC: G10L21/10 ,  G06V10/82 ,  G06V20/40 ,  G06V40/16

Abstract: In a model training method, a computing device generates an initial virtual human speaking video based on an audio data set and a person speaking video. The computing device trains a lip synchronization parameter generation model based on the audio data set and a lip synchronization training parameter used as a model training label. The computing device then uses the lip synchronization parameter generation model to generate a lip synchronization parameter based on input audio, and the lip synchronization parameter is used to drive a virtual human to speak. The computing device expands a data amount of the lip synchronization training parameter by using the initial virtual human speaking video.