Let's face it: Probabilistic multi-modal interlocutor-aware generation of facial gestures in dyadic settings
Preprint
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) subjective and objective experiments assessing the use and relative importance of the different modalities in the synthesized output. The results show that the model successfully leverages the input from the interlocutor to generate more appropriate behavior.Keywords
All Related Versions
- Version 1, 2020-06-11, ArXiv
- Version 2, 2020-10-22, ArXiv
- Published version: , 1.
This publication has 13 references indexed in Scilit:
- OpenFace 2.0: Facial Behavior Analysis Toolkit2018
- Limiting the reconstruction capability of generative neural network using negative learning2017
- Audio-driven facial animation by joint end-to-end learning of pose and emotionACM Transactions on Graphics, 2017
- The MAHNOB Mimicry Database: A database of naturalistic human interactionsPattern Recognition Letters, 2015
- Representing Affective Facial Expressions for Robots and Embodied Conversational Agents by Facial LandmarksInternational Journal of Social Robotics, 2013
- Digital ChameleonsPsychological Science, 2005
- Face recognition based on fitting a 3D morphable modelIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- The power of a nod and a glance: Envelope vs. emotional feedback in animated conversational agentsApplied Artificial Intelligence, 1999
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- Facial Action Coding System1978