All You Need Is Your Voice: Emotional Face Representation with Audio Perspective for Emotional Talking Face Generation

초록

With the rise of generative models, multi-modal video generation has gained significant attention, particularly in the realm of audio-driven emotional talking face synthesis. This paper addresses two key challenges in this domain: Input bias and intensity saturation. A novel neutralization scheme is first proposed to counter input bias, yielding impressive results in generating neutral talking faces from emotionally expressive ones. Furthermore, 2D continuous emotion label-based regression learning effectively generates varying emotional intensities on a frame basis. Results from a user study quantify subjective interpretations of strong emotions and naturalness, revealing up to 78.09% higher emotion accuracy and up to 3.41 higher naturalness score compared to the lowest-ranked method https://github.com/sbde500/EAP.

키워드