Spoken dialogue technology - toward the conversational user interface

What would you say if your refrigerator told you, " You're having some friends round for hot chocolate later. Maybe you should order two cartons of milk " ? Of course, in Spoken Dialogue Technology, Michael McTear will not give an answer to the question of whether talking to domestic appliances makes sense, but he indicates that even a normal household, for instance, may offer a wide field of application for spoken-language dialogue systems in the near future. Consequently his book primarily focuses on theory and practice of these systems. Addressing undergraduate students as well as postgraduate researchers and practitioners in human-computer interfaces, the book is subdivided into three parts which meet the readers' needs: " Background to Spoken Dialogue Technology " (Chapters 1– 5), " Developing Spoken Dialogue Applications " (Chapters 6 –11), and " Advanced Applications " (Chapters 12–14). Chapter 1, " Talking with Computers: Fact or Fiction, " and Chapter 2, " Spoken Dialogue Applications: Research Directions and Commercial Deployment, " present recent products and aspects of dialogue technology as well as historical linguistic and artificial intelligence approaches to dialogue and simulated conversation. Aspects of present-day commercial use of spoken dialogue technology are also discussed. In Chapter 3, " Understanding Dialogue, " the term dialogue is defined, and four of its key characteristics—dialogue as discourse, dialogue as purposeful activity, dialogue as collaborative activity, and utterances in dialogue—and its structures and processes are described in detail. Chapter 4 gives an overview of the components of a spoken language dialogue system: speech recognition, language understanding, language generation, and text-to-speech synthesis. The central component (i.e., dialogue management) is specified in Chapter 5. Here, dialogue initiative (system initiative, user initiative, and mixed initiative), dialogue control (finite-state-based, frame-based, and agent-based control), and grounding (how to process the user's input) are described. Furthermore, knowledge sources (dialogue history, task record, world knowledge model, domain model, generic model, and user model) and problems that arise when interacting with an external knowledge source are discussed. The second part starts with dialogue engineering, which can be subdivided into analysis and specification of requirements, design, implementation, testing, and evaluation of a dialogue system. The use-case analysis includes user profile (type of user, language, user's experience level, etc.) and usage profile (frequency of use, input/output device type, environment, etc.). The spoken-language requirements can