AI RESEARCH
Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation
arXiv CS.CV
•
ArXi:2604.25255v1 Announce Type: new Speech-preserving facial expression manipulation (SPFEM) aims to enhance human expressiveness without altering mouth movements tied to the original speech. A primary challenge in this domain is the scarcity of paired data, namely aligned frames of the same individual with identical speech but different expressions, which impedes direct supervision for emotional manipulation. While current Visual-Language Models (VLMs) can extract aligned visual and semantic features, making them a promising source of supervision, their direct application is limited.