# PASE: Phoneme-Aware Speech Encoder to Improve Lip Sync Accuracy for Talking Head Synthesis

arXiv: https://arxiv.org/abs/2504.05803 · HTML: https://mlsanity.com/paper/2504.05803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 30 of 34)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation](https://mlsanity.com/paper/2104.11116/) (2021)
- [Deep Video Portraits](https://mlsanity.com/paper/1805.11714/) (2018)
- [Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle](https://mlsanity.com/paper/2312.03431/) (2023)
- [EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions](https://mlsanity.com/paper/2407.08136/) (2024)
- [A Tutorial on Principal Component Analysis](https://mlsanity.com/paper/1404.1100/) (2014)
- [Realistic Speech-Driven Facial Animation with GANs](https://mlsanity.com/paper/1906.06337/) (2019)
- [DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation](https://mlsanity.com/paper/2301.03786/) (2023)
- [GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis](https://mlsanity.com/paper/2301.13430/) (2023)
- [Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency](https://mlsanity.com/paper/2409.02634/) (2024)
- [SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis](https://mlsanity.com/paper/2311.17590/) (2023)
- [Everybody's Talkin': Let Me Talk as You Want](https://mlsanity.com/paper/2001.05201/) (2020)
- [Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition](https://mlsanity.com/paper/2211.12368/) (2022)
- [Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis](https://mlsanity.com/paper/2307.09323/) (2023)
- [TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting](https://mlsanity.com/paper/2404.15264/) (2024)
- [GAIA: Zero-shot Talking Avatar Generation](https://mlsanity.com/paper/2311.15230/) (2023)
- [GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation](https://mlsanity.com/paper/2305.00787/) (2023)
- [Learned Spatial Representations for Few-shot Talking-Head Synthesis](https://mlsanity.com/paper/2104.14557/) (2021)
- [AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis](https://mlsanity.com/paper/2312.10921/) (2023)

## Abstract (arXiv)

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.