A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation

TL;DR

This paper introduces a multi-scale generative approach that improves natural head motion and audio-visual synchrony in talking head animation, addressing both short-term lip movements and long-term head dynamics.

Contribution

It proposes a novel multi-scale audio-visual synchrony loss and a multi-scale autoregressive GAN for enhanced speech-driven head motion generation.

Findings

Significant improvements in head motion dynamics quality.

Enhanced multi-scale audio-visual synchrony.

Outperforms state-of-the-art on benchmark datasets.

Abstract

Animating still face images with deep generative models using a speech input signal is an active research topic and has seen important recent progress.However, much of the effort has been put into lip syncing and rendering quality while the generation of natural head motion, let alone the audio-visual correlation between head motion and speech, has often been neglected.In this work, we propose a multi-scale audio-visual synchrony loss and a multi-scale autoregressive GAN to better handle short and long-term correlation between speech and the dynamics of the head and lips.In particular, we train a stack of syncer models on multimodal input pyramids and use these models as guidance in a multi-scale generator network to produce audio-aligned motion unfolding over diverse time scales.Both the pyramid of audio-visual syncers and the generative models are trained in a low-dimensional space that fully preserves dynamics cues.The experiments show significant improvements over the state-of-the-art in head motion dynamics quality and especially in multi-scale audio-visual synchrony on a collection of benchmark datasets.