# Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video

arXiv: https://arxiv.org/abs/2309.04814 · HTML: https://mlsanity.com/paper/2309.04814/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 9 Sep 2023.

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

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (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)
- [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)
- [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)
- [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)
- [Lip Reading Sentences in the Wild](https://mlsanity.com/paper/1611.05358/) (2016)
- [Talking Face Generation by Adversarially Disentangled Audio-Visual Representation](https://mlsanity.com/paper/1807.07860/) (2018)
- [MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement](https://mlsanity.com/paper/2104.08223/) (2021)
- [X2Face: A network for controlling face generation by using images, audio, and pose codes](https://mlsanity.com/paper/1807.10550/) (2018)
- [Lip Movements Generation at a Glance](https://mlsanity.com/paper/1803.10404/) (2018)
- [Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion](https://mlsanity.com/paper/2107.09293/) (2021)
- [Realistic Speech-Driven Facial Animation with GANs](https://mlsanity.com/paper/1906.06337/) (2019)
- [Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation](https://mlsanity.com/paper/2201.07786/) (2022)
- [Talking-head Generation with Rhythmic Head Motion](https://mlsanity.com/paper/2007.08547/) (2020)
- [You said that?](https://mlsanity.com/paper/1705.02966/) (2017)
- [Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis](https://mlsanity.com/paper/2207.11770/) (2022)
- [One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning](https://mlsanity.com/paper/2112.02749/) (2021)
- [Everybody's Talkin': Let Me Talk as You Want](https://mlsanity.com/paper/2001.05201/) (2020)
- [DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering](https://mlsanity.com/paper/2201.00791/) (2022)
- [ObamaNet: Photo-realistic lip-sync from text](https://mlsanity.com/paper/1801.01442/) (2017)

## Built on by (most cited first, 11 of 11)

- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis](https://mlsanity.com/paper/2403.08764/) (2024)
- [TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model](https://mlsanity.com/paper/2410.10696/) (2024)
- [ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer](https://mlsanity.com/paper/2408.03284/) (2024)
- [Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication](https://mlsanity.com/paper/2403.19467/) (2024)
- [ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model](https://mlsanity.com/paper/2503.21144/) (2025)
- [Delving Deep into Engagement Prediction of Short Videos](https://mlsanity.com/paper/2410.00289/) (2024)
- [JEAN: Joint Expression and Audio-guided NeRF-based Talking Face Generation](https://mlsanity.com/paper/2409.12156/) (2024)
- [GMTalker: Gaussian Mixture-based Audio-Driven Emotional Talking Video Portraits](https://mlsanity.com/paper/2312.07669/) (2023)
- [A Speech-to-Video Synthesis Approach Using Spatio-Temporal Diffusion for Vocal Tract MRI](https://mlsanity.com/paper/2503.12102/) (2025)
- [G4G:A Generic Framework for High Fidelity Talking Face Generation with Fine-grained Intra-modal Alignment](https://mlsanity.com/paper/2402.18122/) (2024)

## Abstract (arXiv)

Synthesizing realistic videos according to a given speech is still an open challenge. Previous works have been plagued by issues such as inaccurate lip shape generation and poor image quality. The key reason is that only motions and appearances on limited facial areas (e.g., lip area) are mainly driven by the input speech. Therefore, directly learning a mapping function from speech to the entire head image is prone to ambiguity, particularly when using a short video for training. We thus propose a decomposition-synthesis-composition framework named Speech to Lip (Speech2Lip) that disentangles speech-sensitive and speech-insensitive motion/appearance to facilitate effective learning from limited training data, resulting in the generation of natural-looking videos. First, given a fixed head pose (i.e., canonical space), we present a speech-driven implicit model for lip image generation which concentrates on learning speech-sensitive motion and appearance. Next, to model the major speech-insensitive motion (i.e., head movement), we introduce a geometry-aware mutual explicit mapping (GAMEM) module that establishes geometric mappings between different head poses. This allows us to paste generated lip images at the canonical space onto head images with arbitrary poses and synthesize talking videos with natural head movements. In addition, a Blend-Net and a contrastive sync loss are introduced to enhance the overall synthesis performance. Quantitative and qualitative results on three benchmarks demonstrate that our model can be trained by a video of just a few minutes in length and achieve state-of-the-art performance in both visual quality and speech-visual synchronization. Code: https://github.com/CVMI-Lab/Speech2Lip.