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 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.
@inproceeding{eungi2024enhancing,
title={Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert},
author={EunGi, Han and Hyun-Bin, Oh and Sung-Bin, Kim and Nivelet Etcheberry, Corentin and Nam, Suekyeong and Ju, Janghoon and Oh, Tae-Hyun},
booktitle={INTERSPEECH 2024},
year={2024}
}
This research was supported by a grant from KRAFTON AI. This work was partially supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.RS-2023-00225630, Development of Artificial Intelligence for Text-based 3D Movie Generation; No.RS-2022-II220290, Visual Intelligence for Space-Time Understanding and Generation based on Multi-layered Visual Common Sense; No.RS-2019-II191906, Artificial Intelligence Graduate School Program(POSTECH))