Let's Face It: Probabilistic Multi-modal Interlocutor-aware Generation of Facial Gestures in Dyadic Settings

TL;DR

This paper presents a probabilistic, interlocutor-aware facial gesture generation method for conversational agents, leveraging multi-modal cues and extending a recent motion synthesis model to produce more natural and contextually appropriate non-verbal behaviors.

Contribution

The paper introduces a novel probabilistic approach that incorporates multi-modal interlocutor cues into facial gesture synthesis, extending MoGlow for more natural and adaptive agent behaviors.

Findings

Model effectively uses multi-modal cues to generate appropriate gestures.

Probabilistic method reduces repetitive motions compared to deterministic approaches.

Subjective evaluation confirms improved naturalness and appropriateness of generated gestures.

Abstract

To enable more natural face-to-face interactions, conversational agents need to adapt their behavior to their interlocutors. One key aspect of this is generation of appropriate non-verbal behavior for the agent, for example facial gestures, here defined as facial expressions and head movements. Most existing gesture-generating systems do not utilize multi-modal cues from the interlocutor when synthesizing non-verbal behavior. Those that do, typically use deterministic methods that risk producing repetitive and non-vivid motions. In this paper, we introduce a probabilistic method to synthesize interlocutor-aware facial gestures - represented by highly expressive FLAME parameters - in dyadic conversations. Our contributions are: a) a method for feature extraction from multi-party video and speech recordings, resulting in a representation that allows for independent control and manipulation of expression and speech articulation in a 3D avatar; b) an extension to MoGlow, a recent motion-synthesis method based on normalizing flows, to also take multi-modal signals from the interlocutor as input and subsequently output interlocutor-aware facial gestures; and c) a subjective evaluation assessing the use and relative importance of the input modalities. The results show that the model successfully leverages the input from the interlocutor to generate more appropriate behavior. Videos, data, and code available at: https://jonepatr.github.io/lets_face_it.