Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose

TL;DR

This paper introduces a neural network model that synthesizes realistic talking face videos with personalized head movements, expressions, and lip sync by leveraging audio, a short target video, and 3D face reconstruction.

Contribution

It presents a novel approach combining 3D face animation and a memory-augmented GAN to generate personalized head pose and expressions from minimal target video data.

Findings

Produces high-quality talking face videos with natural head movements

Requires only about 300 frames of target video for personalization

Outperforms state-of-the-art methods in realism and head movement naturalness

Abstract

Real-world talking faces often accompany with natural head movement. However, most existing talking face video generation methods only consider facial animation with fixed head pose. In this paper, we address this problem by proposing a deep neural network model that takes an audio signal A of a source person and a very short video V of a target person as input, and outputs a synthesized high-quality talking face video with personalized head pose (making use of the visual information in V), expression and lip synchronization (by considering both A and V). The most challenging issue in our work is that natural poses often cause in-plane and out-of-plane head rotations, which makes synthesized talking face video far from realistic. To address this challenge, we reconstruct 3D face animation and re-render it into synthesized frames. To fine tune these frames into realistic ones with smooth background transition, we propose a novel memory-augmented GAN module. By first training a general mapping based on a publicly available dataset and fine-tuning the mapping using the input short video of target person, we develop an effective strategy that only requires a small number of frames (about 300 frames) to learn personalized talking behavior including head pose. Extensive experiments and two user studies show that our method can generate high-quality (i.e., personalized head movements, expressions and good lip synchronization) talking face videos, which are naturally looking with more distinguishing head movement effects than the state-of-the-art methods.