Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert

TL;DR

This paper presents a novel audio-visual perceptual loss and a lip reading expert to improve the realism and intelligibility of speech-driven 3D facial animations, especially focusing on lip synchronization and readability.

Contribution

It introduces an audio-visual multimodal perceptual loss and a lip reading expert to enhance lip movement accuracy in speech-driven 3D facial animation.

Findings

Improved lip synchronization accuracy

Enhanced lip readability in animations

Effective integration of audio-visual cues

Abstract

Speech-driven 3D facial animation has recently garnered attention due to its cost-effective usability in multimedia production. However, most current advances overlook the intelligibility of lip movements, limiting the realism of facial expressions. In this paper, we introduce a method for speech-driven 3D facial animation to generate accurate lip movements, proposing an audio-visual multimodal perceptual loss. This loss provides guidance to train the speech-driven 3D facial animators to generate plausible lip motions aligned with the spoken transcripts. Furthermore, to incorporate the proposed audio-visual perceptual loss, we devise an audio-visual lip reading expert leveraging its prior knowledge about correlations between speech and lip motions. We validate the effectiveness of our approach through broad experiments, showing noticeable improvements in lip synchronization and lip readability performance. Codes are available at https://3d-talking-head-avguide.github.io/.