FluentLip: A Phonemes-Based Two-stage Approach for Audio-Driven Lip Synthesis with Optical Flow Consistency
By: Shiyan Liu, Rui Qu, Yan Jin
Potential Business Impact:
Makes talking videos look and sound real.
Generating consecutive images of lip movements that align with a given speech in audio-driven lip synthesis is a challenging task. While previous studies have made strides in synchronization and visual quality, lip intelligibility and video fluency remain persistent challenges. This work proposes FluentLip, a two-stage approach for audio-driven lip synthesis, incorporating three featured strategies. To improve lip synchronization and intelligibility, we integrate a phoneme extractor and encoder to generate a fusion of audio and phoneme information for multimodal learning. Additionally, we employ optical flow consistency loss to ensure natural transitions between image frames. Furthermore, we incorporate a diffusion chain during the training of Generative Adversarial Networks (GANs) to improve both stability and efficiency. We evaluate our proposed FluentLip through extensive experiments, comparing it with five state-of-the-art (SOTA) approaches across five metrics, including a proposed metric called Phoneme Error Rate (PER) that evaluates lip pose intelligibility and video fluency. The experimental results demonstrate that our FluentLip approach is highly competitive, achieving significant improvements in smoothness and naturalness. In particular, it outperforms these SOTA approaches by approximately $\textbf{16.3%}$ in Fr\'echet Inception Distance (FID) and $\textbf{35.2%}$ in PER.
Similar Papers
FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs
CV and Pattern Recognition
Makes talking faces match any voice perfectly.
Text2Lip: Progressive Lip-Synced Talking Face Generation from Text via Viseme-Guided Rendering
CV and Pattern Recognition
Makes any text speak with a realistic face.
LTA-L2S: Lexical Tone-Aware Lip-to-Speech Synthesis for Mandarin with Cross-Lingual Transfer Learning
Sound
Makes computers talk like people by reading lips.