Voice User Interface Design 2004
Authors: Cohen M. H. Giangola J. P. Balogh J.
Published year: 2005
Pages: 5-6/117
Buy this book on amazon.com >>

Praise for Voice User Interface Design

"Mike Cohen is a giant in the field of speech technology. He and his co-authors bring years of valuable experience in VUI design to life in this new book. It is a must read for anyone designing user interfaces."

—John Kelly
Editor-in-Chief
Speech Technology Magazine

"VUI design is a challenging combination of art, science, and process. The authors of Voice User Interface Design augment their extensive real-world experience with a thoughtful perspective on how to think about the process. And they get into the details necessary to deliver an effective voice interface. The book removes much of the mystery behind this new and critical discipline."

—Bill Meisel
Publisher and Editor
Speech Recognition Update

"The strength of Voice User Interface Design over others in the area is its depth and grounding in the research literature. More importantly, it does not pretend to offer a cookbook to VUI design, but rather a set of well-informed design principles, and gives credit to the intelligence of the reader to apply these principles to specific problems."

—Chris Schmandt
Principal Research Scientist
M.I.T. Media Lab

"Most current speech recognition systems can recognize a single word as well as, if not better than a human being. Yet building an effective voice system is still a significant challenge. Voice User Interface Design meets the challenge by providing the necessary background and steps to produce an effective VUI. Organized around a financial brokerage design example, the book is a comprehensive, yet approachable treatment of all that is necessary for building a successful voice application. From analyzing the differences between written and spoken language to prompt design and prosody planning, Voice User Interface Design should quickly become the standard reference for all involved in voice application design."

—Harry M. Hersh
The Users Voice


About the Authors and Radio Rex

Michael Cohen cofounded Nuance Communications in 1994. He has served in a variety of roles at Nuance, including Vice President of Dialog R&D. He created the Nuance Professional Services team, which engages with customers to design and deploy applications, and led the group through the first 22 deployments of Nuance technology. He created the Dialog R&D group , which has been responsible for voice user interface research, for Nuance's natural language understanding technology (including Say Anything and Accuroute), and for designs of interfaces for products such as Voyager, the Nuance voice browser.

Before founding Nuance, Michael was at SRI International for more than 10 years . At SRI he led numerous projects in acoustic modeling and speech technology development. He led the SRI ATIS project, which combined speech recognition and natural language understanding technology to create an early spoken language understanding system.

Michael has published more than 70 papers and holds eight patents related to speech and VUI technology. He is a frequent speaker at conferences and industry trade shows. Michael is a consulting professor at Stanford University and serves on the board of directors of the Applied Voice Input/Output Society (AVIOS). He received his Ph.D. in computer science from UC Berkeley.

In his spare time, Michael composes and plays music. In the summer of 2000, his band , the Mike Cohen Sextet, performed at the Montreux Jazz Festival.

James Giangola considers himself an "industrial linguist," on a mission to apply principles of natural conversation, from prosody to the discourse level, to engineered dialogs. In addition to dialog design, his expertise includes speech synthesis, concatenation planning and production, and voice coaching. No matter the area of interface design, however, his overriding concern is to offer the user a familiar linguistic experience, and therefore one that is comfortable and comprehensible. James's design philosophy is not limited to English-language interfaces; he has also helped to create natural-sounding, persona-rich interfaces in French, Portuguese, German, and Japanese.

James holds linguistics degrees from Brown University, the Monterey Institute of International Studies, and U.C. San Diego, and he has 10 years of experience teaching languages at the high school and university level. He is also the author of The Pronunciation of Brazilian Portuguese (Munich: Lincom Europa, 2001).

James resides in Salvador, Brazil, where he maintains a linguistic consulting business for American and Brazilian companies needing help with interface design and brand naming.

Jennifer Balogh is a Speech Consultant at Nuance Communications, where she designs and evaluates interfaces for spoken language systems. She has worked on deployed applications for customers such as AT&T, Charles Schwab, and TD Waterhouse and has contributed to a number of Nuance products, including Nuance Call Steering, the Vocalizer TTS engine, the voice browser Voyager, and SpeechObjects. She has also conducted research on dialog design techniques that optimize user satisfaction and holds several patents.

Previously, she researched language disorders at the Aphasia Research Center at the Boston VA Hospital. She also cofounded Phaedrus Internet Development, Inc., a Web solutions provider for corporations and medical institutions. She has presented at conferences such as CHI Conference on Human Factors in Computing Systems and CUNY Conference on Human Sentence Processing. She has also lectured for courses at Stanford University, UC San Diego, University of San Francisco, and University of San Diego. Jennifer has published several papers in journals such as Brain and Language and International Journal of Speech Technology . She received her Ph.D. in psychology from UC San Diego and holds a B.A. from Brandeis University.

Radio Rex , pictured on the cover of the book, was the first automated spoken language understanding system ever developed. Rex was first produced in 1911. Unlike many spoken language systems developed over the following eight decades, it was a commercial success! Radio Rex was a children's toy. Rex sat in his doghouse until the child said "Rex," at which point he would eagerly jump out. The technology behind Rex is briefly described at the beginning of Chapter 2.

Photo of Radio Rex courtesy of Hy Murveit. Rex himself courtesy of the private toy collection of Michael Cohen.

Voice User Interface Design 2004
Authors: Cohen M. H. Giangola J. P. Balogh J.
Published year: 2005
Pages: 5-6/117
Buy this book on amazon.com >>