Издательство Springer, 2005, -422 pp.
This book is based on publications from the ISCA Tutorial and Research Workshop on Multi-Modal Dialogue in Mobile Environments held at Kloster Irsee, Germany, in 2002. The workshop covered various aspects of development and evaluation of spoken multimodal dialogue systems and components with particular emphasis on mobile environments, and discussed the state-ofthe- art within this area. On the development side the major aspects addressed include speech recognition, dialogue management, multimodal output generation, system architectures, full applications, and user interface issues. On the evaluation side primarily usability evaluation was addressed. A number of high quality papers from the workshop were selected to form the basis of this book.
The volume is divided into three major parts which group together the overall aspects covered by the workshop. The selected papers have all been extended, reviewed and improved after the workshop to form the backbone of the book. In addition, we have supplemented each of the three parts by an invited contribution intended to serve as an overview chapter.
Part one of the volume covers issues in multimodal spoken dialogue systems and components. The overview chapter surveys multimodal dialogue systems and links up to the other chapters in part one. These chapters discuss aspects of speech recognition, dialogue management and multimodal output generation.
Part two covers system architecture and example implementations. The overview chapter provides a survey of architecture and standardisation issues while the remainder of this part discusses architectural issues mostly based on fully implemented, practical applications. Part three concerns evaluation and usability. The human factors aspect is a very important one both from a development point of view and when it comes to evaluation. The overview chapter presents the state-of-the-art in evaluation and usability and also outlines novel challenges in the area. The other chapters in this part illustrate and discuss various approaches to evaluation and usability in concrete applications or experiments that often require one or more novel challenges to be addressed.
We are convinced that computer scientists, engineers, and others who work in the area of spoken multimodal dialogue systems, no matter if in academia or in industry, may find the volume interesting and useful to their own work. Graduate students and PhD students specialising in spoken multimodal dialogue systems more generally, or focusing on issues in such systems in mobile environments in particular, may also use this book to get a concrete idea of how far research is today in the area and of some of the major issues to consider when developing spoken multimodal dialogue systems in practice.
Part I Issues in Multimodal Spoken Dialogue Systems and ComponentsMultimodal Dialogue Systems
Speech Recognition Technology in Multimodal/Ubiquitous Computing Environments
A Robust Multimodal Speech Recognition Method using Optical Flow Analysis
Feature Functions for Tree-Based Dialogue Course Management
A Reasoning Component for Information-Seeking and Planning
A Model for Multimodal Dialogue System Output Applied to an Animated Talking Head
Part II System Architecture and Example ImplementationsOverview of System Architecture
XISL: A Modality-Independent MMI Description Language
A Path to Multimodal Data Services for Telecommunications
Multimodal Spoken Dialogue with Wireless Devices
The SmartKom Mobile Car Prototype System for Flexible Human-Machine Communication
LARRI: A Language-Based Maintenance and Repair Assistant
Part III Evaluation and UsabilityOverview of Evaluation and Usability
Evaluating Dialogue Strategies in Multimodal Dialogue Systems
Enhancing the Usability of Multimodal Virtual Co-drivers
Design, Implementation and Evaluation of the SENECA Spoken Language Dialogue System
Segmenting Route Descriptions for Mobile Devices
Effects of Prolonged Use on the Usability of a Multimodal Form-Filling Interface
User Multitasking with Mobile Multimodal Systems
Speech Convergence with Animated Personas