READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Haotian, Weng, Yuzhe, Du, Jun, Xu, Haoran, Wu, Xiaoyan, He, Shan, Yin, Bing, Liu, Cong, Gao, Jianqing, Liu, Qingfeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908655531589632
author Wang, Haotian
Weng, Yuzhe
Du, Jun
Xu, Haoran
Wu, Xiaoyan
He, Shan
Yin, Bing
Liu, Cong
Gao, Jianqing
Liu, Qingfeng
author_facet Wang, Haotian
Weng, Yuzhe
Du, Jun
Xu, Haoran
Wu, Xiaoyan
He, Shan
Yin, Bing
Liu, Cong
Gao, Jianqing
Liu, Qingfeng
contents The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking head generation models. In this study, we propose READ, a real-time diffusion-transformer-based talking head generation framework. Our approach first learns a spatiotemporal highly compressed video latent space via a temporal VAE, significantly reducing the token count to accelerate generation. To achieve better audio-visual alignment within this compressed latent space, a pre-trained Speech Autoencoder (SpeechAE) is proposed to generate temporally compressed speech latent codes corresponding to the video latent space. These latent representations are then modeled by a carefully designed Audio-to-Video Diffusion Transformer (A2V-DiT) backbone for efficient talking head synthesis. Furthermore, to ensure temporal consistency and accelerated inference in extended generation, we propose a novel asynchronous noise scheduler (ANS) for both the training and inference processes of our framework. The ANS leverages asynchronous add-noise and asynchronous motion-guided generation in the latent space, ensuring consistency in generated video clips. Experimental results demonstrate that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime, achieving an optimal balance between quality and speed while maintaining robust metric stability in long-time generation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03457
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation
Wang, Haotian
Weng, Yuzhe
Du, Jun
Xu, Haoran
Wu, Xiaoyan
He, Shan
Yin, Bing
Liu, Cong
Gao, Jianqing
Liu, Qingfeng
Graphics
Computer Vision and Pattern Recognition
Sound
Audio and Speech Processing
The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking head generation models. In this study, we propose READ, a real-time diffusion-transformer-based talking head generation framework. Our approach first learns a spatiotemporal highly compressed video latent space via a temporal VAE, significantly reducing the token count to accelerate generation. To achieve better audio-visual alignment within this compressed latent space, a pre-trained Speech Autoencoder (SpeechAE) is proposed to generate temporally compressed speech latent codes corresponding to the video latent space. These latent representations are then modeled by a carefully designed Audio-to-Video Diffusion Transformer (A2V-DiT) backbone for efficient talking head synthesis. Furthermore, to ensure temporal consistency and accelerated inference in extended generation, we propose a novel asynchronous noise scheduler (ANS) for both the training and inference processes of our framework. The ANS leverages asynchronous add-noise and asynchronous motion-guided generation in the latent space, ensuring consistency in generated video clips. Experimental results demonstrate that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime, achieving an optimal balance between quality and speed while maintaining robust metric stability in long-time generation.
title READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation
topic Graphics
Computer Vision and Pattern Recognition
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2508.03457