ReNeLiB: Real-time Neural Listening Behavior Generation for Socially Interactive Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Don, Daksitha Withanage, Müller, Philipp, Nunnari, Fabrizio, André, Elisabeth, Gebhard, Patrick
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911776167165952
author Don, Daksitha Withanage
Müller, Philipp
Nunnari, Fabrizio
André, Elisabeth
Gebhard, Patrick
author_facet Don, Daksitha Withanage
Müller, Philipp
Nunnari, Fabrizio
André, Elisabeth
Gebhard, Patrick
contents Flexible and natural nonverbal reactions to human behavior remain a challenge for socially interactive agents (SIAs) that are predominantly animated using hand-crafted rules. While recently proposed machine learning based approaches to conversational behavior generation are a promising way to address this challenge, they have not yet been employed in SIAs. The primary reason for this is the lack of a software toolkit integrating such approaches with SIA frameworks that conforms to the challenging real-time requirements of human-agent interaction scenarios. In our work, we for the first time present such a toolkit consisting of three main components: (1) real-time feature extraction capturing multi-modal social cues from the user; (2) behavior generation based on a recent state-of-the-art neural network approach; (3) visualization of the generated behavior supporting both FLAME-based and Apple ARKit-based interactive agents. We comprehensively evaluate the real-time performance of the whole framework and its components. In addition, we introduce pre-trained behavioral generation models derived from psychotherapy sessions for domain-specific listening behaviors. Our software toolkit, pivotal for deploying and assessing SIAs' listening behavior in real-time, is publicly available. Resources, including code, behavioural multi-modal features extracted from therapeutic interactions, are hosted at https://daksitha.github.io/ReNeLib
format Preprint
id arxiv_https___arxiv_org_abs_2402_08079
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ReNeLiB: Real-time Neural Listening Behavior Generation for Socially Interactive Agents
Don, Daksitha Withanage
Müller, Philipp
Nunnari, Fabrizio
André, Elisabeth
Gebhard, Patrick
Human-Computer Interaction
Flexible and natural nonverbal reactions to human behavior remain a challenge for socially interactive agents (SIAs) that are predominantly animated using hand-crafted rules. While recently proposed machine learning based approaches to conversational behavior generation are a promising way to address this challenge, they have not yet been employed in SIAs. The primary reason for this is the lack of a software toolkit integrating such approaches with SIA frameworks that conforms to the challenging real-time requirements of human-agent interaction scenarios. In our work, we for the first time present such a toolkit consisting of three main components: (1) real-time feature extraction capturing multi-modal social cues from the user; (2) behavior generation based on a recent state-of-the-art neural network approach; (3) visualization of the generated behavior supporting both FLAME-based and Apple ARKit-based interactive agents. We comprehensively evaluate the real-time performance of the whole framework and its components. In addition, we introduce pre-trained behavioral generation models derived from psychotherapy sessions for domain-specific listening behaviors. Our software toolkit, pivotal for deploying and assessing SIAs' listening behavior in real-time, is publicly available. Resources, including code, behavioural multi-modal features extracted from therapeutic interactions, are hosted at https://daksitha.github.io/ReNeLib
title ReNeLiB: Real-time Neural Listening Behavior Generation for Socially Interactive Agents
topic Human-Computer Interaction
url https://arxiv.org/abs/2402.08079