Advances in Natural Multimodal Dialogue Systems

The main topic of this volume is natural multimodal interaction. The book is unique in that it brings together a great many contributions regarding aspects of natural and multimodal interaction written by many of the important actors in the field. It is a timely update of Multimodality in Language and Speech Systems by Björn Granström, David House and Inger Karlsson and, at the same time, it presents a much broader overview of the field. Its 17 chapters provide a broad and detailed impression of where the fairly new field of natural and multimodal interactivity engineering stands today. Topics addressed include talking heads, conversational agents, tutoring systems, multimodal communication, machine learning, architectures for multimodal dialogue systems, systems evaluation, and data annotation.This title will prove very valuable to scientists, researchers and practitioners working in the fields of natural interactive systems, multimodal systems, conversational agents, spoken dialogue systems, natural language processing applications, advanced human-computer interfaces, analysis of multimodal data, evaluation of multimodal systems, and educational systems. TOC:From the contents:Preface. Natural and Multimodal Interactivity Engineering - Directions and Needs.- I: Making Dialogues More Natural: Empirical Work and Applied Theory; Social Dialogue with Embodied Conversational Agents. A First Experiment in Engagement for Human-Robot Interaction in Hosting Activities.- II: Annotation and Analysis of Multimodal Data: Speech and Gesture; FORM. On the Relationships among Speech, Gestures, and Object Manipulation in Virtual Environments: Initial Evidence. Analysing Multimodal Communication. Do Oral Messages Help Visual Search? Geometric and Statistical Approaches to Audiovisual Segmentation.- III: Animated Talking Heads and Evaluation; The Psychology and Technology of Talking Heads: Applications in Language Learning. Effective Interaction with Talking Animated Agents in Dialogue Systems. Controlling the Gaze of Conversational Agents.- IV: Architectures and Technologies for Advanced and Adaptive Multimodal Dialogue Systems. MIND: A Context-Based Multimodal Interpretation Framework in Conversational Systems. A General Purpose Architecture for Intelligent Tutoring Systems. MIAMM - A Multimodal Dialogue System using Haptics. Adaptive Human-Computer Dialogue. Machine Learning Approaches to Human Dialogue Modelling. Index.