# Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation

arXiv: https://arxiv.org/abs/2109.10595 · HTML: https://mlsanity.com/paper/2109.10595/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 86 references that are in the map.
- First posted on arXiv 22 Sep 2021.

## Builds on (most cited first, 30 of 56)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [Video-to-Video Synthesis](https://mlsanity.com/paper/1808.06601/) (2018)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [MakeItTalk: Speaker-Aware Talking-Head Animation](https://mlsanity.com/paper/2004.12992/) (2020)
- [Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation](https://mlsanity.com/paper/2104.11116/) (2021)
- [Few-Shot Adversarial Learning of Realistic Neural Talking Head Models](https://mlsanity.com/paper/1905.08233/) (2019)
- [Deep Video Portraits](https://mlsanity.com/paper/1805.11714/) (2018)
- [Capture, Learning, and Synthesis of 3D Speaking Styles](https://mlsanity.com/paper/1905.03079/) (2019)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss](https://mlsanity.com/paper/1905.03820/) (2019)

## Built on by (most cited first, 30 of 36)

- [SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation](https://mlsanity.com/paper/2211.12194/) (2022)
- [Identity-Preserving Talking Face Generation with Landmark and Appearance Priors](https://mlsanity.com/paper/2305.08293/) (2023)
- [Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis](https://mlsanity.com/paper/2211.14506/) (2022)
- [StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator](https://mlsanity.com/paper/2305.05445/) (2023)
- [FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion](https://mlsanity.com/paper/2309.11306/) (2023)
- [SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces](https://mlsanity.com/paper/2306.10799/) (2023)
- [Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization](https://mlsanity.com/paper/2308.09716/) (2023)
- [Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis](https://mlsanity.com/paper/2411.19509/) (2024)
- [High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning](https://mlsanity.com/paper/2305.02572/) (2023)
- [DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation](https://mlsanity.com/paper/2203.07931/) (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)
- [Speech Driven Video Editing via an Audio-Conditioned Diffusion Model](https://mlsanity.com/paper/2301.04474/) (2023)
- [GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting](https://mlsanity.com/paper/2404.14037/) (2024)
- [Few-Shot Head Swapping in the Wild](https://mlsanity.com/paper/2204.13100/) (2022)
- [TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model](https://mlsanity.com/paper/2410.10696/) (2024)
- [Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model](https://mlsanity.com/paper/2503.16942/) (2025)
- [Audio-Visual Face Reenactment](https://mlsanity.com/paper/2210.02755/) (2022)
- [GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting](https://mlsanity.com/paper/2404.16012/) (2024)
- [PersonaTalk: Bring Attention to Your Persona in Visual Dubbing](https://mlsanity.com/paper/2409.05379/) (2024)
- [Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication](https://mlsanity.com/paper/2403.19467/) (2024)
- [Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook](https://mlsanity.com/paper/2411.19537/) (2024)
- [Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator](https://mlsanity.com/paper/2305.02594/) (2023)
- [EmoFace: Audio-driven Emotional 3D Face Animation](https://mlsanity.com/paper/2407.12501/) (2024)
- [Parametric Implicit Face Representation for Audio-Driven Facial Reenactment](https://mlsanity.com/paper/2306.07579/) (2023)
- [Audio-driven High-resolution Seamless Talking Head Video Editing via StyleGAN](https://mlsanity.com/paper/2407.05577/) (2024)
- [Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions](https://mlsanity.com/paper/2507.02900/) (2025)
- [MusicFace: Music-driven Expressive Singing Face Synthesis](https://mlsanity.com/paper/2303.14044/) (2023)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)
- [Style Transfer for 2D Talking Head Animation](https://mlsanity.com/paper/2303.09799/) (2023)
- [FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model](https://mlsanity.com/paper/2408.09384/) (2024)

## Abstract (arXiv)

To the best of our knowledge, we first present a live system that generates personalized photorealistic talking-head animation only driven by audio signals at over 30 fps. Our system contains three stages. The first stage is a deep neural network that extracts deep audio features along with a manifold projection to project the features to the target person's speech space. In the second stage, we learn facial dynamics and motions from the projected audio features. The predicted motions include head poses and upper body motions, where the former is generated by an autoregressive probabilistic model which models the head pose distribution of the target person. Upper body motions are deduced from head poses. In the final stage, we generate conditional feature maps from previous predictions and send them with a candidate image set to an image-to-image translation network to synthesize photorealistic renderings. Our method generalizes well to wild audio and successfully synthesizes high-fidelity personalized facial details, e.g., wrinkles, teeth. Our method also allows explicit control of head poses. Extensive qualitative and quantitative evaluations, along with user studies, demonstrate the superiority of our method over state-of-the-art techniques.