DR2: Disentangled Recurrent Representation Learning for Data-Efficient Speech Video Synthesis

Although substantial progress has been made in audio-driven talking video synthesis, there still remain two major difficulties: existing works 1) need a long sequence of training dataset (>1h) to synthesize co-speech gestures, which causes a significant limitation on their applicability; 2) usually fail to generate long sequences, or can only generate long sequences without enough diversity. To solve these challenges, we propose a Disentangled Recurrent Representation Learning framework to synthesize long diversified gesture sequences with a short training video of around 2 minutes. In our framework, we first make a disentangled latent space assumption to encourage unpaired audio and pose combinations, which results in diverse "one-to-many" mappings in pose generation. Next, we apply a recurrent inference module to feed back the last generation as initial guidance to the next phase, enhancing the long-term video generation of full continuity and diversity. Comprehensive experimental results verify that our model can generate realistic synchronized full-body talking videos with training data efficiency.