# PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features

arXiv: https://arxiv.org/abs/2312.02781 · HTML: https://mlsanity.com/paper/2312.02781/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 54 references that are in the map.
- First posted on arXiv 5 Dec 2023.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [Capture, Learning, and Synthesis of 3D Speaking Styles](https://mlsanity.com/paper/1905.03079/) (2019)
- [Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss](https://mlsanity.com/paper/1905.03820/) (2019)
- [Neural Voice Puppetry: Audio-driven Facial Reenactment](https://mlsanity.com/paper/1912.05566/) (2019)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction](https://mlsanity.com/paper/2003.13989/) (2020)
- [MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement](https://mlsanity.com/paper/2104.08223/) (2021)
- [CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior](https://mlsanity.com/paper/2301.02379/) (2023)
- [Audio-Driven Emotional Video Portraits](https://mlsanity.com/paper/2104.07452/) (2021)
- [Depth-Aware Generative Adversarial Network for Talking Head Video Generation](https://mlsanity.com/paper/2203.06605/) (2022)
- [EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation](https://mlsanity.com/paper/2303.11089/) (2023)
- [SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces](https://mlsanity.com/paper/2306.10799/) (2023)
- [Speech Driven Talking Face Generation from a Single Image and an Emotion Condition](https://mlsanity.com/paper/2008.03592/) (2020)
- [Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview](https://mlsanity.com/paper/2105.14291/) (2021)
- [Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image](https://mlsanity.com/paper/2204.01586/) (2022)
- [FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2303.05416/) (2023)
- [Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels](https://mlsanity.com/paper/2201.05986/) (2022)
- [AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person](https://mlsanity.com/paper/2108.04325/) (2021)
- [Joint Audio-Text Model for Expressive Speech-Driven 3D Facial Animation](https://mlsanity.com/paper/2112.02214/) (2021)
- [Learning Audio-Driven Viseme Dynamics for 3D Face Animation](https://mlsanity.com/paper/2301.06059/) (2023)
- [3D-TalkEmo: Learning to Synthesize 3D Emotional Talking Head](https://mlsanity.com/paper/2104.12051/) (2021)
- [Audio-Driven Dubbing for User Generated Contents via Style-Aware Semi-Parametric Synthesis](https://mlsanity.com/paper/2309.00030/) (2023)
- [MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation](https://mlsanity.com/paper/2303.09797/) (2023)

## Built on by (most cited first, 6 of 6)

- [Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions](https://mlsanity.com/paper/2507.02900/) (2025)
- [MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding](https://mlsanity.com/paper/2507.06071/) (2025)
- [PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation](https://mlsanity.com/paper/2412.07754/) (2024)
- [PESTalk: Speech-Driven 3D Facial Animation with Personalized Emotional Styles](https://mlsanity.com/paper/2512.05121/) (2025)
- [Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction](https://mlsanity.com/paper/2607.13646/) (2026)
- [PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification](https://mlsanity.com/paper/2607.24052/) (2026)

## Abstract (arXiv)

Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading to unsatisfactory results in terms of precision and coherence. We argue that visual and textual cues are not trivial information. Therefore, we present a novel framework, namely PMMTalk, using complementary Pseudo Multi-Modal features for improving the accuracy of facial animation. The framework entails three modules: PMMTalk encoder, cross-modal alignment module, and PMMTalk decoder. Specifically, the PMMTalk encoder employs the off-the-shelf talking head generation architecture and speech recognition technology to extract visual and textual information from speech, respectively. Subsequently, the cross-modal alignment module aligns the audio-image-text features at temporal and semantic levels. Then PMMTalk decoder is employed to predict lip-syncing facial blendshape coefficients. Contrary to prior methods, PMMTalk only requires an additional random reference face image but yields more accurate results. Additionally, it is artist-friendly as it seamlessly integrates into standard animation production workflows by introducing facial blendshape coefficients. Finally, given the scarcity of 3D talking face datasets, we introduce a large-scale 3D Chinese Audio-Visual Facial Animation (3D-CAVFA) dataset. Extensive experiments and user studies show that our approach outperforms the state of the art. We recommend watching the supplementary video.