Empowering Dialogue Systems with Affective and Adaptive Interaction: Integrating Social Intelligence
Authors:
- 10 September 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
As spoken language technologies continue to rapidly advance, the need for more natural human-computer interaction in our daily lives becomes increasingly apparent to leverage the full potential of Spoken Dialogue Systems (SDSs). In this paper, we identify key advances needed to empower machines with social intelligence in spoken language interaction from both perception and synthesis aspects. To illustrate the limitations of current SDSs, we outline two social intelligence capabilities that are present in human conversations but not yet fully realized in machines, namely affect anticipation and voice adaptation. We provide experimental analysis of affect anticipation and theoretical analysis of voice adaptation to demonstrate the feasibility and necessity of these capabilities for empowering dialogue systems with affective and adaptive interaction to achieve human-level social intelligence.Keywords
This publication has 47 references indexed in Scilit:
- Turn-taking in Conversational Systems and Human-Robot Interaction: A ReviewComputer Speech & Language, 2021
- Social Robots on a Global Stage: Establishing a Role for Culture During Human–Robot InteractionInternational Journal of Social Robotics, 2020
- Empathetic Speech Synthesis and Testing for Healthcare RobotsInternational Journal of Social Robotics, 2020
- Evaluations of an artificial intelligence instructor's voice: Social Identity Theory in human-robot interactionsComputers in Human Behavior, 2019
- SSML for Sex Robots2018
- Impact of personality on the cerebral processing of emotional prosodyNeuroImage, 2011
- Anticipation and Emotion2010
- IEMOCAP: interactive emotional dyadic motion capture databaseLanguage Resources and Evaluation, 2008
- Automatic discrimination between laughter and speechSpeech Communication, 2007
- Implementation and testing of a system for producing emotion-by-rule in synthetic speechSpeech Communication, 1995