Издательство Springer, 2010, -351 pp.
In recent years spoken language research has been successful in establishing technology which can be used in various applications, and which has also brought forward novel research topics that advance our understanding of the human speech and communication processes in general. This book got started in order to collect these different trends together, and to provide an overview of the current state of the art, as well as of the challenging research topics that deal with spoken language interaction technologies.
The topics have been broadly divided into two main classes: research on the enabling technology on one hand and applications that exemplify the use of the technology on the other hand. Each chapter is an independent review of a specific topic, covering research problems and possible solutions, and also envisaging development of the field in the near future. The basic technology development covers areas such as automatic speech recognition and speech synthesis, spoken dialogue systems and dialogue modelling, expressive speech synthesis, emotions and affective computing, multimodal communication and animated agents, while the applications concern speech translation, spoken language usage in cars, space, and military applications, as well as applications for special user groups.
Discussion of the general evaluation methodologies is also included in the book. The authors are leading figures of their field. Their experience provides a strong basis for the discussion of various aspects of the specific research topic and, in addition to their own work, for the presentation of a broad view of the entire research area. The core topics are discussed from the research, engineering, and industrial perspectives, and together the chapters provide an integrated view of the research and development in speech and spoken dialogue technology, representing a comprehensive view of the whole area.
The structure of the contributions follows a general format that consists of presenting the current state of the art in the particular research area, including a short history and development of the research as the background, and then discussing and evaluating new trends and view points related to the future of the field. Concerning different applications, the articles address both technical and usability issues, e.g. they provide an analysis of the factors that affect the application’s real-time functioning, and usability requirements concerning their specific interaction and design issues.
The book is intended for readers, both in industry and academia, who wish to get a summary of the current research and development in the speech technology and its related fields. The aim of the book is to highlight main research questions and possible solutions so as to clarify the existing technological possibilities for the design and development of spoken language interactive systems, and also to inspire experimentation of new techniques, methods, models, and applications in speech technology and interaction studies. It also serves as a reference book to the historical development of the field and its various subfields, and as a collection of future visions of the research directions.
The spoken interaction research field has made great advances during the past years, and is active, maybe even more than ever, with a wide range of research topics. Many challenges need to be addressed, and new topics will obviously come across during the investigations. As a part of the joint efforts in research and development, the book will, hopefully, help the development of technologies to go forward, so as to satisfy the requirements of the users, and also our needs to understand human communication better.
History and Development of Speech Recognition
Challenges in Speech Synthesis
Spoken Language Dialogue Models
The Industry of Spoken-Dialog Systems and the Third Generation of Interactive Applications
Deceptive Speech: Clues from Spoken Language
Cognitive Approaches to Spoken Language Technology
Expressive Speech Processing and Prosody Engineering: An Illustrated Essay on the Fragmented Nature of Real Interactive Speech
Interacting with Embodied Conversational Agents
Multimodal Information Processing for Affective Computing
Spoken Language Translation
Application of Speech Technology in Vehicles
Spoken Dialogue Application in Space: The Clarissa Procedure Browser
Military Applications: Human Factors Aspects of Speech-Based Systems
Accessibility and Design for All Solutions Through Speech Technology
Assessment and Evaluation of Speech-Based Interactive Systems: From Manual Annotation to Automatic Usability Evaluation