Interactive Conversational Head Generation

TL;DR

This paper introduces a new benchmark and datasets for synthesizing interactive conversational heads capable of both talking and listening, enabling more realistic face-to-face virtual interactions.

Contribution

It presents novel datasets, ViCo and ViCo-X, and defines three new tasks for interactive conversational head generation, advancing the creation of responsive and expressive virtual agents.

Findings

Baseline methods can generate responsive, vivid conversational agents.

The datasets facilitate training models for multi-turn face-to-face interactions.

Experimental results demonstrate effective collaboration between virtual agents and real persons.

Abstract

We introduce a new conversation head generation benchmark for synthesizing behaviors of a single interlocutor in a face-to-face conversation. The capability to automatically synthesize interlocutors which can participate in long and multi-turn conversations is vital and offer benefits for various applications, including digital humans, virtual agents, and social robots. While existing research primarily focuses on talking head generation (one-way interaction), hindering the ability to create a digital human for conversation (two-way) interaction due to the absence of listening and interaction parts. In this work, we construct two datasets to address this issue, ``ViCo'' for independent talking and listening head generation tasks at the sentence level, and ``ViCo-X'', for synthesizing interlocutors in multi-turn conversational scenarios. Based on ViCo and ViCo-X, we define three novel tasks targeting the interaction modeling during the face-to-face conversation: 1) responsive listening head generation making listeners respond actively to the speaker with non-verbal signals, 2) expressive talking head generation guiding speakers to be aware of listeners' behaviors, and 3) conversational head generation to integrate the talking/listening ability in one interlocutor. Along with the datasets, we also propose corresponding baseline solutions to the three aforementioned tasks. Experimental results show that our baseline method could generate responsive and vivid agents that can collaborate with real person to fulfil the whole conversation. Project page: https://vico.solutions/.