# Shared Latent Representation for Joint Text-to-Audio-Visual Synthesis

arXiv: https://arxiv.org/abs/2511.05432 · HTML: https://mlsanity.com/paper/2511.05432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss](https://mlsanity.com/paper/1905.03820/) (2019)
- [Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert](https://mlsanity.com/paper/2303.17480/) (2023)
- [Identity-Preserving Talking Face Generation with Landmark and Appearance Priors](https://mlsanity.com/paper/2305.08293/) (2023)
- [Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization](https://mlsanity.com/paper/2308.09716/) (2023)
- [HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis](https://mlsanity.com/paper/2311.12454/) (2023)
- [Text2Video: Text-driven Talking-head Video Synthesis with Personalized Phoneme-Pose Dictionary](https://mlsanity.com/paper/2104.14631/) (2021)
- [FT2TF: First-Person Statement Text-To-Talking Face Generation](https://mlsanity.com/paper/2312.05430/) (2023)
- [Faces that Speak: Jointly Synthesising Talking Face and Speech from Text](https://mlsanity.com/paper/2405.10272/) (2024)
- [Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos](https://mlsanity.com/paper/2206.04523/) (2022)
- [Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation](https://mlsanity.com/paper/2405.04327/) (2024)
- [Audio-driven Talking Face Generation with Stabilized Synchronization Loss](https://mlsanity.com/paper/2307.09368/) (2023)
- [OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking](https://mlsanity.com/paper/2504.02433/) (2025)
- [UniFLG: Unified Facial Landmark Generator from Text or Speech](https://mlsanity.com/paper/2302.14337/) (2023)
- [Ada-TTA: Towards Adaptive High-Quality Text-to-Talking Avatar Synthesis](https://mlsanity.com/paper/2306.03504/) (2023)
- [Text-to-Video: a Two-stage Framework for Zero-shot Identity-agnostic Talking-head Generation](https://mlsanity.com/paper/2308.06457/) (2023)
- [Text-driven Talking Face Synthesis by Reprogramming Audio-driven Models](https://mlsanity.com/paper/2306.16003/) (2023)

## Abstract (arXiv)

We propose a text-to-talking-face synthesis framework leveraging latent speech representations from HierSpeech++. A Text-to-Vec module generates Wav2Vec2 embeddings from text, which jointly condition speech and face generation. To handle distribution shifts between clean and TTS-predicted features, we adopt a two-stage training: pretraining on Wav2Vec2 embeddings and finetuning on TTS outputs. This enables tight audio-visual alignment, preserves speaker identity, and produces natural, expressive speech and synchronized facial motion without ground-truth audio at inference. Experiments show that conditioning on TTS-predicted latent features outperforms cascaded pipelines, improving both lip-sync and visual realism.