Emotion-Conditioned Motion Sub-spaces with Flow Matching for Real-Time Audio-Driven Talking Heads

Abstract

Recent advances in audio-driven talking-head synthesis have brought lip-sync precision close to human perception, yet emotional fidelity and real-time inference remain open challenges. Existing pipelines typically disentangle lip articulation, facial expression, and head pose in latent space; this rigid factorization ignores the intrinsic coupling between articulation and affect — e.g., downward lip corners when sad—thus limiting expressiveness. We cast speech-conditioned facial motion as a sample from an emotion-conditioned distribution in a motion latent space. Concretely, we (i) learn a motion dictionary of orthogonal bases with an autoencoder via self-supervision, (ii) construct emotion-conditioned sub-spaces within the latent space, and (iii) design a layer-progressive cross-attention fusion module that modulates a flow-matching sampler with both audio and emotion signals. Only ten reverse ODE steps are required to generate a motion-latent trajectory, enabling real-time end-to-end latency. Extensive experiments on MEAD and RAVDESS show that our method outperforms recent GAN- and diffusion-based baselines in emotion accuracy while running at around 75 FPS on a single desktop GPU. The proposed framework delivers the first emotionally expressive Audio2Face system that simultaneously achieves lip-sync accuracy, affective realism, and real-time performance.