Saved in:
Bibliographic Details
Main Authors: Huang, Yihuan, Liu, Jiajun, Ren, Yanzhen, Xue, Jun, Liu, Wuyang, Sun, Zongkun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.05803
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909846615359488
author Huang, Yihuan
Liu, Jiajun
Ren, Yanzhen
Xue, Jun
Liu, Wuyang
Sun, Zongkun
author_facet Huang, Yihuan
Liu, Jiajun
Ren, Yanzhen
Xue, Jun
Liu, Wuyang
Sun, Zongkun
contents Recent talking head synthesis works typically adopt speech features extracted from large-scale pre-trained acoustic models. However, the intrinsic many-to-many relationship between speech and lip motion causes phoneme-viseme alignment ambiguity, leading to inaccurate and unstable lips. To further improve lip sync accuracy, we propose PASE (Phoneme-Aware Speech Encoder), a novel speech representation model that bridges the gap between phonemes and visemes. PASE explicitly introduces phoneme embeddings as alignment anchors and employs a contrastive alignment module to enhance the discriminability between corresponding audio-visual pairs. In addition, a prediction and reconstruction task is designed to improve robustness under noise and partial modality absence. Experimental results show PASE significantly improves lip sync accuracy and achieves state-of-the-art performance across both NeRF- and 3DGS-based rendering frameworks, outperforming conventional methods based on acoustic features by 13.7 % and 14.2 %, respectively. Importantly, PASE can be seamlessly integrated into diverse talking head pipelines to improve the lip sync accuracy without architectural modifications.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05803
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PASE: Phoneme-Aware Speech Encoder to Improve Lip Sync Accuracy for Talking Head Synthesis
Huang, Yihuan
Liu, Jiajun
Ren, Yanzhen
Xue, Jun
Liu, Wuyang
Sun, Zongkun
Graphics
Computer Vision and Pattern Recognition
Recent talking head synthesis works typically adopt speech features extracted from large-scale pre-trained acoustic models. However, the intrinsic many-to-many relationship between speech and lip motion causes phoneme-viseme alignment ambiguity, leading to inaccurate and unstable lips. To further improve lip sync accuracy, we propose PASE (Phoneme-Aware Speech Encoder), a novel speech representation model that bridges the gap between phonemes and visemes. PASE explicitly introduces phoneme embeddings as alignment anchors and employs a contrastive alignment module to enhance the discriminability between corresponding audio-visual pairs. In addition, a prediction and reconstruction task is designed to improve robustness under noise and partial modality absence. Experimental results show PASE significantly improves lip sync accuracy and achieves state-of-the-art performance across both NeRF- and 3DGS-based rendering frameworks, outperforming conventional methods based on acoustic features by 13.7 % and 14.2 %, respectively. Importantly, PASE can be seamlessly integrated into diverse talking head pipelines to improve the lip sync accuracy without architectural modifications.
title PASE: Phoneme-Aware Speech Encoder to Improve Lip Sync Accuracy for Talking Head Synthesis
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.05803