# Intelligible Lip-to-Speech Synthesis with Speech Units

arXiv: https://arxiv.org/abs/2305.19603 · HTML: https://mlsanity.com/paper/2305.19603/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [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)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Speech Resynthesis from Discrete Disentangled Self-Supervised Representations](https://mlsanity.com/paper/2104.00355/) (2021)
- [Lip Reading Sentences in the Wild](https://mlsanity.com/paper/1611.05358/) (2016)
- [End-to-end Audio-visual Speech Recognition with Conformers](https://mlsanity.com/paper/2102.06657/) (2021)
- [Generative Spoken Dialogue Language Modeling](https://mlsanity.com/paper/2203.16502/) (2022)
- [Lipreading using Temporal Convolutional Networks](https://mlsanity.com/paper/2001.08702/) (2020)
- [Robust Self-Supervised Audio-Visual Speech Recognition](https://mlsanity.com/paper/2201.01763/) (2022)
- [Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis](https://mlsanity.com/paper/2005.08209/) (2020)
- [Sub-word Level Lip Reading With Visual Attention](https://mlsanity.com/paper/2110.07603/) (2021)
- [UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units](https://mlsanity.com/paper/2212.08055/) (2022)
- [Lip to Speech Synthesis with Visual Context Attentional GAN](https://mlsanity.com/paper/2204.01726/) (2022)
- [Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading](https://mlsanity.com/paper/2204.01725/) (2022)
- [SVTS: Scalable Video-to-Speech Synthesis](https://mlsanity.com/paper/2205.02058/) (2022)
- [Lip-to-Speech Synthesis in the Wild with Multi-task Learning](https://mlsanity.com/paper/2302.08841/) (2023)

## Built on by (most cited first, 28 of 28)

- [DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding](https://mlsanity.com/paper/2308.07787/) (2023)
- [Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge](https://mlsanity.com/paper/2308.09311/) (2023)
- [AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation](https://mlsanity.com/paper/2312.02512/) (2023)
- [Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper](https://mlsanity.com/paper/2309.08535/) (2023)
- [AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation](https://mlsanity.com/paper/2508.00733/) (2025)
- [Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation](https://mlsanity.com/paper/2308.01831/) (2023)
- [VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models](https://mlsanity.com/paper/2504.02386/) (2025)
- [From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech](https://mlsanity.com/paper/2503.16956/) (2025)
- [Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation](https://mlsanity.com/paper/2401.09802/) (2024)
- [Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction](https://mlsanity.com/paper/2404.12725/) (2024)
- [AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation](https://mlsanity.com/paper/2504.20629/) (2025)
- [V2SFlow: Video-to-Speech Generation with Speech Decomposition and Rectified Flow](https://mlsanity.com/paper/2411.19486/) (2024)
- [Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis](https://mlsanity.com/paper/2504.13386/) (2025)
- [Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-training and Multi-modal Tokens](https://mlsanity.com/paper/2309.08531/) (2023)
- [NaturalL2S: End-to-End High-quality Multispeaker Lip-to-Speech Synthesis with Differential Digital Signal Processing](https://mlsanity.com/paper/2502.12002/) (2025)
- [LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models](https://mlsanity.com/paper/2505.11391/) (2025)
- [DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization](https://mlsanity.com/paper/2603.14267/) (2026)
- [RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations](https://mlsanity.com/paper/2307.01233/) (2023)
- [DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility](https://mlsanity.com/paper/2503.05223/) (2025)
- [RESOUND: Speech Reconstruction from Silent Videos via Acoustic-Semantic Decomposed Modeling](https://mlsanity.com/paper/2505.22024/) (2025)
- [LTA-L2S: Lexical Tone-Aware Lip-to-Speech Synthesis for Mandarin with Cross-Lingual Transfer Learning](https://mlsanity.com/paper/2509.25670/) (2025)
- [The Role of Prosodic and Lexical Cues in Turn-Taking with Self-Supervised Speech Representations](https://mlsanity.com/paper/2601.13835/) (2026)
- [CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing](https://mlsanity.com/paper/2604.12292/) (2026)
- [VisualSpeech: Enhancing Prosody Modeling in TTS Using Video](https://mlsanity.com/paper/2501.19258/) (2025)
- [UniCUE: Unified Recognition and Generation Framework for Chinese Cued Speech Video-to-Speech Generation](https://mlsanity.com/paper/2506.04134/) (2025)
- [MuteSwap: Visual-informed Silent Video Identity Conversion](https://mlsanity.com/paper/2507.00498/) (2025)
- [SLD-L2S: Hierarchical Subspace Latent Diffusion for High-Fidelity Lip to Speech Synthesis](https://mlsanity.com/paper/2602.11477/) (2026)
- [Watch Your Speech: Text-aware Video-to-Speech Synthesis with Textual Conditioning](https://mlsanity.com/paper/2610.01012/) (2026)

## Abstract (arXiv)

In this paper, we propose a novel Lip-to-Speech synthesis (L2S) framework, for synthesizing intelligible speech from a silent lip movement video. Specifically, to complement the insufficient supervisory signal of the previous L2S model, we propose to use quantized self-supervised speech representations, named speech units, as an additional prediction target for the L2S model. Therefore, the proposed L2S model is trained to generate multiple targets, mel-spectrogram and speech units. As the speech units are discrete while mel-spectrogram is continuous, the proposed multi-target L2S model can be trained with strong content supervision, without using text-labeled data. Moreover, to accurately convert the synthesized mel-spectrogram into a waveform, we introduce a multi-input vocoder that can generate a clear waveform even from blurry and noisy mel-spectrogram by referring to the speech units. Extensive experimental results confirm the effectiveness of the proposed method in L2S.