Designing Style Matching Conversational Agents

10/16/2019
by   Deepali Aneja, et al.
0

Advances in machine intelligence have enabled conversational interfaces that have the potential to radically change the way humans interact with machines. However, even with the progress in the abilities of these agents, there remain critical gaps in their capacity for natural interactions. One limitation is that the agents are often monotonic in behavior and do not adapt to their partner. We built two end-to-end conversational agents: a voice-based agent that can engage in naturalistic, multi-turn dialogue and align with the interlocutor's conversational style, and a 2nd, expressive, embodied conversational agent (ECA) that can recognize human behavior during open-ended conversations and automatically align its responses to the visual and conversational style of the other party. The embodied conversational agent leverages multimodal inputs to produce rich and perceptually valid vocal and facial responses (e.g., lip syncing and expressions) during the conversation. Based on empirical results from a set of user studies, we highlight several significant challenges in building such systems and provide design guidelines for multi-turn dialogue interactions using style adaptation for future research.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/04/2019

An End-to-End Conversational Style Matching Agent

We present an end-to-end voice-based conversational agent that is able t...
research
08/29/2023

FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions

We demonstrate an embodied conversational agent that can function as a r...
research
01/31/2019

Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue

We consider the problem of designing an artificial agent capable of inte...
research
06/21/2017

A Generative Model of Group Conversation

Conversations with non-player characters (NPCs) in games are typically c...
research
03/08/2021

Let's be friends! A rapport-building 3D embodied conversational agent for the Human Support Robot

Partial subtle mirroring of nonverbal behaviors during conversations (al...
research
09/01/2021

Building a Legal Dialogue System: Development Process, Challenges and Opportunities

This paper presents key principles and solutions to the challenges faced...
research
08/21/2020

Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodology

Conversational interfaces are increasingly popular as a way of connectin...

Please sign up or login with your details

Forgot password? Click here to reset