Talking-head video editing aims to efficiently insert, delete, and
substitutethewordofapre-recordedvideothroughatexttranscript
editor. The key challenge for this task is obtaining an editing model
that generates new talking-head video clips which simultaneously
have accurate lip synchronization and motion smoothness. Pre-
vious approaches, including 3DMM-based (3D Morphable Model)
methods and NeRF-based (Neural Radiance Field) methods, are sub-
optimal in that they either require minutes of source videos and
days of training time or lack the disentangled control of verbal (e.g.,
lip motion) and non-verbal (e.g., head pose and expression) repre-
sentations for video clip insertion. In this work, we fully utilize the
video context to design a novel framework for talking-head video
editing, which achieves efficiency, disentangled motion control, and