Voice User Interface Design, 1st edition

Published by Addison-Wesley Professional (February 2, 2004) © 2004

  • James P. Giangola
  • Jennifer Balogh
$51.99

  • A print text (hardcover or paperback) 
  • Free shipping
  • Also available for purchase as an ebook from all major ebook resellers, including InformIT.com

This book shows how to design, deploy, and assess VUIs. The book itself combines discussion of essential VUI design principles and practical methodology with real-world examples of good design. It should become the standard reference to VUI.

By far the most comprehensive guide to voice user interface design available, written by the most experienced practitioners in the field

° Automated speech recognition applications are poised for phenomenal growth, because they provide companies with a distinct competitive advantage

° Important design principles and guidelines are illustrated using a running sample application

° The companion website will have audio clips for all the examples in the book, which will bring the examples to life for the reader



About the Authors and Radio Rex.


Preface.

I. INTRODUCTION.

1. Introduction to Voice User Interfaces.

What Is a Voice User Interface?

Why Speech?

Where Do We Go from Here?

2. Overview of Spoken Language Technology.

Architecture of a Spoken Language System.

The Impact of Speech Technology on Design Decisions.

Conclusion.

3. Overview of the Methodology.

Methodological Principles.

Steps of the Methodology.

Applying the Methodology to Real-World Applications.

Conclusion.

II. DEFINITION PHASE: REQUIREMENTS GATHERING AND HIGH-LEVEL DESIGN.

4. Requirements and High-Level Design Methodology.

Requirements Definition.

High-Level Design.

Conclusion.

5. High-Level Design Elements.

Dialog Strategy and Grammar Type.

Pervasive Dialog Elements.

Conclusion.

6. Creating Persona, by Design.

What Is Persona?

Where Does Persona Come From?

A Checklist for Persona Design.

Persona Definition.

Conclusion.

7. Sample Application: Requirements and High-Level Design.

Lexington Brokerage.

Requirements Definition.

High-Level Design.

Conclusion.

III. DESIGN PHASE: DETAILED DESIGN.

8. Detailed Design Methodology.

Anatomy of a Dialog State.

Call Flow Design.

Prompt Design.

User Testing.

Design Principles.

Conclusion.

9. Minimizing Cognitive Load.

Conceptual Complexity.

Memory Load.

Attention.

Conclusion.

10. Designing Prompts.

Conversation as Discourse.

Cohesion.

Information Structure.

Spoken Versus Written English.

Register and Consistency.

Jargon.

The Cooperative Principle.

Conclusion.

11. Planning Prosody.

What Is Prosody?

Functions of Prosody.

Stress.

Intonation.

Concatenating Phone Numbers.

Minimizing Concatenation Splices.

Pauses.

TTS Guidelines.

Conclusion.

12. Maximizing Efficiency and Clarity.

Efficiency.

Clarity.

Balancing Efficiency and Clarity.

Conclusion.

13. Optimizing Accuracy and Recovering from Errors.

Measuring Accuracy.

Dialog Design Guidelines for Maximizing Accuracy.

Recovering from Errors.

Conclusion.

14. Sample Application: Detailed Design.

Call Flow Design.

Prompt Design.

User Testing.

Conclusion.

IV. REALIZATION PHASE: DEVELOPMENT, TESTING, AND TUNING.

15. Development, Testing, and Tuning Methodology.

Development.

Testing.

Tuning.

Conclusion.

16. Creating Grammars.

Grammar Development.

Grammar Testing.

Grammar Tuning.

Conclusion.

17. Working with Voice Actors.

Scripting for Success.

Choosing Your Voice Actor.

Running a Recording Session.

Conclusion.

18. Sample Application: Development, Testing, and Tuning.

Development.

Testing.

Tuning.

19. Conclusion.

Appendix.

Bibliography.

Index.

Michael Cohen is the cofounder of Nuance Communications. He has played a variety of roles at Nuance, including creation of the Professional Services organization and the Dialog Research and Development group. Michael is a popular speaker and a consulting professor at Stanford University. He has published more than seventy papers, holds eight patents.

James Giangola is an industrial linguist, who designs, researches, and mentors others in creating VUIs that reflect the linguistic features and principles that shape everyday, human-to-human conversations. An innovator in prompt-writing and dialog design, James has ten years of experience teaching languages and linguistics, and maintains a consulting practice.

Jennifer Balogh is a speech consultant at Nuance Communications, where she designs and evaluates interfaces for spoken language systems. She also conducts research on dialog design techniques and holds several patents. Jennifer is a university lecturer and frequent contributor to conferences and journals.


0321185765AB11172003

Need help? Get in touch

Video
Play
Privacy and cookies
By watching, you agree Pearson can share your viewership data for marketing and analytics for one year, revocable by deleting your cookies.

Pearson eTextbook: What’s on the inside just might surprise you

They say you can’t judge a book by its cover. It’s the same with your students. Meet each one right where they are with an engaging, interactive, personalized learning experience that goes beyond the textbook to fit any schedule, any budget, and any lifestyle.Â