# Shushing! Let's Imagine an Authentic Speech from the Silent Video

arXiv: https://arxiv.org/abs/2503.14928 · HTML: https://mlsanity.com/paper/2503.14928/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 52 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data](https://mlsanity.com/paper/2406.03736/) (2024)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [Diffsound: Discrete Diffusion Model for Text-to-sound Generation](https://mlsanity.com/paper/2207.09983/) (2022)
- [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023)
- [Attention is All You Need in Speech Separation](https://mlsanity.com/paper/2010.13154/) (2020)
- [Score-based Continuous-time Discrete Diffusion Models](https://mlsanity.com/paper/2211.16750/) (2022)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [Concrete Score Matching: Generalized Score Matching for Discrete Data](https://mlsanity.com/paper/2211.00802/) (2022)
- [FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis](https://mlsanity.com/paper/2204.09934/) (2022)
- [Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis](https://mlsanity.com/paper/2005.08209/) (2020)
- [Lip to Speech Synthesis with Visual Context Attentional GAN](https://mlsanity.com/paper/2204.01726/) (2022)
- [EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance](https://mlsanity.com/paper/2211.09496/) (2022)
- [SVTS: Scalable Video-to-Speech Synthesis](https://mlsanity.com/paper/2205.02058/) (2022)
- [Learning to Dub Movies via Hierarchical Prosody Models](https://mlsanity.com/paper/2212.04054/) (2022)
- [Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech](https://mlsanity.com/paper/2302.13700/) (2023)
- [POSTER++: A simpler and stronger facial expression recognition network](https://mlsanity.com/paper/2301.12149/) (2023)
- [V2C: Visual Voice Cloning](https://mlsanity.com/paper/2111.12890/) (2021)
- [LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading](https://mlsanity.com/paper/2306.03258/) (2023)

## Built on by (most cited first, 1 of 1)

- [FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing](https://mlsanity.com/paper/2505.01263/) (2025)

## Abstract (arXiv)

Vision-guided speech generation aims to produce authentic speech from facial appearance or lip motions without relying on auditory signals, offering significant potential for applications such as dubbing in filmmaking and assisting individuals with aphonia. Despite recent progress, existing methods struggle to achieve unified cross-modal alignment across semantics, timbre, and emotional prosody from visual cues, prompting us to propose Consistent Video-to-Speech (CV2S) as an extended task to enhance cross-modal consistency. To tackle emerging challenges, we introduce ImaginTalk, a novel cross-modal diffusion framework that generates faithful speech using only visual input, operating within a discrete space. Specifically, we propose a discrete lip aligner that predicts discrete speech tokens from lip videos to capture semantic information, while an error detector identifies misaligned tokens, which are subsequently refined through masked language modeling with BERT. To further enhance the expressiveness of the generated speech, we develop a style diffusion transformer equipped with a face-style adapter that adaptively customizes identity and prosody dynamics across both the channel and temporal dimensions while ensuring synchronization with lip-aware semantic features. Extensive experiments demonstrate that ImaginTalk can generate high-fidelity speech with more accurate semantic details and greater expressiveness in timbre and emotion compared to state-of-the-art baselines. Demos are shown at our project page: https://imagintalk.github.io.