Designing Voice User Interfaces: Principles of Conversational Experiences

by Cathy Pearl

Overview

Voice user interfaces (VUIs) are becoming all the rage today. But how do you build one that people can actually converse with? Whether you’re designing a mobile app, a toy, or a device such as a home assistant, this practical book guides you through basic VUI design principles, helps you choose the right speech recognition engine, and shows you how to measure your VUI’s performance and improve upon it.

Author Cathy Pearl also takes product managers, UX designers, and VUI designers into advanced design topics that will help make your VUI not just functional, but great.

• Understand key VUI design concepts, including command-and-control and conversational systems
• Decide if you should use an avatar or other visual representation with your VUI
• Explore speech recognition technology and its impact on your design
• Take your VUI above and beyond the basic exchange of information
• Learn practical ways to test your VUI application with users
• Monitor your app and learn how to quickly improve performance
• Get real-world examples of VUIs for home assistants, smartwatches, and car systems

Product Details

ISBN-13:	9781491955413
Publisher:	O'Reilly Media, Incorporated
Publication date:	12/31/2016
Pages:	275
Product dimensions:	5.90(w) x 8.90(h) x 0.70(d)

About the Author

Cathy Pearl is Head of Conversation Design Outreach at Google. She's been designing and creating Voice User Interfaces (VUIs) for nearly 20 years and is passionate about helping everyone make the best conversational experiences possible. Previously, Cathy was VP of User Experience at Sensely, whose virtual nurse avatar helps people stay healthy. She has worked on everything from programming NASA helicopter pilot simulators to designing a conversational iPad app in which Esquire magazine's style columnist tells users what they should wear on a first date. She has an MS in Computer Science from Indiana Universityand a BS in Cognitive Science from UC San Diego.

Table of Contents

Preface xi

Chapter 1 Introduction 1

A Brief History of VUIs 1

Conversational User Interfaces 5

What Is a VUI Designer? 8

Chatbots 9

Conclusion 12

Chapter 2 Basic Voice User Interface Design Principles 13

Designing for Mobile Devices Versus IVR Systems 13

Conversational Design 16

Setting User Expectations 19

Design Tools 21

Confirmations 24

Command-and-Control Versus Conversational 32

Conversational Markers 34

Error Handling 41

Don't Blame the User 47

Novice and Expert Users 47

Keeping Track of Context 49

Help and Other Universals 53

Latency 56

Disambiguation 58

Design Documentation 60

Accessibility 61

Conclusion 69

Chapter 3 Personas, Avatars, Actors, and Video Games 71

Personas 71

Should My VUI Be Seen? 75

Using an Avatar: What Not to Do 77

Using an Avatar (or Recorded Video): What to Do 79

When Should I Use Video in My VUI? 86

Visual VUI-Best Practices 87

Visual (Non-Avatar) Feedback 95

Choosing a Voice 98

Pros of an Avatar 99

The Downsides of an Avatar 101

Conclusion 104

Chapter 4 Speech Recognition Technology 107

Choosing an Engine 107

Barge-In 109

N-Best Lists 120

The Challenges of Speech Recognition 122

Data Privacy 127

Conclusion 128

Chapter 5 Advanced Voice User Interface Design 129

Branching Based on Voice Input 130

Disambiguation 134

Handling Negation 140

Capturing Intent and Objects 141

Dialog Management 142

Don't Leave Your User Hanging 144

Should the VUI Display What It Recognized? 144

Sentiment Analysis and Emotion Detection 146

Text-to-Speech Versus Recorded Speech 148

Speaker Verification 151

"Wake" Words 152

Context 153

Advanced Multimodal 154

Bootstrapping Datasets 154

Advanced NLU 156

Conclusion 160

Chapter 6 User Testing for Voice User Interfaces 161

Special VUI Considerations 161

Background Research on Users and Use Cases 162

Designing a Study with Real Users 163

Early-Stage Testing 173

Usability Testing 179

Performance Measures 184

Next Steps 186

Testing VUIS in Cars, Devices, and Robots 186

Conclusion 188

Chapter 7 Your Voice User Interface Is Finished! Now What? 191

Prerelease Testing 191

Measuring Performance 195

Logging 205

Transcription 206

Release Phases 207

Surveys 208

Analysis 209

Tools 214

Conclusion 216

Chapter 8 Voice-Enabled Devices and Cars 219

Devices 219

Cars and Autonomous Vehicles 232

Conclusion 242

Epilogue 243

Appendix A Products Mentioned in This Book 245

Index 247