A Distributed Architecture for Real-time Dialogue and On-task Learning of Efficient Co-operative Turn-taking - Coverbal Synchrony in Human-Machine Interaction - page 293

CHAPTER 12
A Distributed Architecture
for Real-time Dialogue and
On-task Learning of Efficient
Co-operative Turn-taking
Gudny Ragna Jonsdottir and Kristinn R. Thórisson
1. Introduction
Building automatic dialogue systems that match human flexibility and
reactivity has proven difficult. Many factors impede the progress of
such systems, useful as they may be, from the low-level of real-time
audio signal analysis and noise filtering to medium-level turn-taking
cues and control signals, all the way up to high-level dialogue intent
and content-related interpretation. Of these, we have focussed on
the dynamics of turn-taking—the real-time 1 control of who has the
turn and how turns are exchanged and how to integrate these in an
expandable architecture for dialogue generation and control. Manual
categorization of silences, prosody and other candidate turn-giving
signals, or analysis of corpora to produce static decision trees for
this purpose cannot address the high within- and between-individual
variability observed in natural interaction. As an alternative, we have
1 By “real-time” here we mean conducting dialogue at a pace acceptable to, and in line
with, human expectations, as understood and learned from real-world experience.