# Audio2Face: Generating Speech/Face Animation from Single Audio with Attention-Based Bidirectional LSTM Networks

arXiv: https://arxiv.org/abs/1905.11142 · HTML: https://mlsanity.com/paper/1905.11142/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2019.

## Built on by (most cited first, 8 of 8)

- [EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation](https://mlsanity.com/paper/2303.11089/) (2023)
- [FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization](https://mlsanity.com/paper/2403.06375/) (2024)
- [LaughTalk: Expressive 3D Talking Head Generation with Laughter](https://mlsanity.com/paper/2311.00994/) (2023)
- [Say Anything with Any Style](https://mlsanity.com/paper/2403.06363/) (2024)
- [Meta-Learning Empowered Meta-Face: Personalized Speaking Style Adaptation for Audio-Driven 3D Talking Face Animation](https://mlsanity.com/paper/2408.09357/) (2024)
- [PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance](https://mlsanity.com/paper/2406.09326/) (2024)
- [Expressive Speech-driven Facial Animation with controllable emotions](https://mlsanity.com/paper/2301.02008/) (2023)
- [One Shot Audio to Animated Video Generation](https://mlsanity.com/paper/2102.09737/) (2021)

## Abstract (arXiv)

We propose an end to end deep learning approach for generating real-time facial animation from just audio. Specifically, our deep architecture employs deep bidirectional long short-term memory network and attention mechanism to discover the latent representations of time-varying contextual information within the speech and recognize the significance of different information contributed to certain face status. Therefore, our model is able to drive different levels of facial movements at inference and automatically keep up with the corresponding pitch and latent speaking style in the input audio, with no assumption or further human intervention. Evaluation results show that our method could not only generate accurate lip movements from audio, but also successfully regress the speaker's time-varying facial movements.