DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

TL;DR

DualTalk introduces a unified framework for realistic 3D talking head conversations that seamlessly handle speaking and listening roles, improving naturalness and expressiveness in dual-speaker interactions.

Contribution

The paper presents a novel task and a unified model that captures dynamic speaker-listener behaviors in 3D talking head generation, along with a new dataset for multi-round conversations.

Findings

Enhanced naturalness of 3D talking heads in dual conversations

Significant improvement in expressiveness and realism

Effective modeling of speaker-listener role interplay

Abstract

In face-to-face conversations, individuals need to switch between speaking and listening roles seamlessly. Existing 3D talking head generation models focus solely on speaking or listening, neglecting the natural dynamics of interactive conversation, which leads to unnatural interactions and awkward transitions. To address this issue, we propose a new task -- multi-round dual-speaker interaction for 3D talking head generation -- which requires models to handle and generate both speaking and listening behaviors in continuous conversation. To solve this task, we introduce DualTalk, a novel unified framework that integrates the dynamic behaviors of speakers and listeners to simulate realistic and coherent dialogue interactions. This framework not only synthesizes lifelike talking heads when speaking but also generates continuous and vivid non-verbal feedback when listening, effectively capturing the interplay between the roles. We also create a new dataset featuring 50 hours of multi-round conversations with over 1,000 characters, where participants continuously switch between speaking and listening roles. Extensive experiments demonstrate that our method significantly enhances the naturalness and expressiveness of 3D talking heads in dual-speaker conversations. We recommend watching the supplementary video: https://ziqiaopeng.github.io/dualtalk.