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

TL;DR

This paper introduces an end-to-end deep learning model using bidirectional LSTM and attention mechanisms to generate real-time facial animations from audio, capturing lip movements and facial expressions without manual intervention.

Contribution

The novel approach combines bidirectional LSTM and attention to accurately generate facial animations directly from audio, improving realism and synchronization.

Findings

Accurately generates lip movements from audio.

Successfully regresses time-varying facial expressions.

Operates in real-time without human intervention.

Abstract

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.