O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Art and Business of Speech Recognition: Creating the Noble Voice, The

Book Description

Most people have experienced an automated speech-recognition system when calling a company. Instead of prompting callers to choose an option by entering numbers, the system asks questions and understands spoken responses. With a more advanced application, callers may feel as if they're having a conversation with another person. Not only will the system respond intelligently, its voice even has personality.

The Art and Business of Speech Recognition examines both the rapid emergence and broad potential of speech-recognition applications. By explaining the nature, design, development, and use of such applications, this book addresses two particular needs:

  1. Business managers must understand the competitive advantage that speech-recognition applications provide: a more effective way to engage, serve, and retain customers over the phone.

  2. Application designers must know how to meet their most critical business goal: a satisfying customer experience.

Author Blade Kotelly illuminates these needs from the perspective of an experienced, business-focused practitioner. Among the diverse applications he's worked on, perhaps his most influential design is the flight-information system developed for United Airlines, about which Julie Vallone wrote in Investor's Business Daily: "By the end of the conversation, you might want to take the voice to dinner."

If dinner is the analogy, this concise book is an ideal first course. Managers will learn the potential of speech-recognition applications to reduce costs, increase customer satisfaction, enhance the company brand, and even grow revenues. Designers, especially those just beginning to work in the voice domain, will learn user-interface design principles and techniques needed to develop and deploy successful applications. The examples in the book are real, the writing is accessible and lucid, and the solutions presented are attainable today.


Table of Contents

  1. Copyright
  2. Praise for the Art and Business of Speech Recognition
  3. Preface
  4. The Background
    1. On Telephones, Touchtones, and Business Needs
      1. Speech Recognition Versus Touchtone Functionality
      2. Problems with Touchtone, and a Speech Recognition Remedy
      3. What Kinds of Companies are Using Speech Recognition?
      4. Why are Companies Using It?
      5. Speech-Recognition Applications: A Typical Example
      6. Where We've Been—Where We're Going
    2. Technology Primer: About Speech Recognizers
      1. What the Recognizer Hears (and the Need for Confirmation)
      2. When the Recognizer Listens
      3. Why Designing a Speech-Recognition Application Is Challenging
      4. Where We've Been—Where We're Going
    3. The Psychology of How People Interact with Speech-Recognition Systems
      1. Social-Psychological Research
      2. Ask “Dr.” Blade
      3. Where We've Been—Where We're Going
  5. The Process of Designing Speech-Recognition Systems
    1. Research
      1. Clients' Objectives
      2. Callers' Objectives and Needs
      3. Aspects of Research
      4. Assembling a Requirements Specification
      5. Anticipating Change
      6. Where We've Been—Where We're Going
    2. Developing the Design
      1. Conceptualizing and Brainstorming
      2. Congruence of Style
      3. Defining the Call Flow
      4. Vision Clips/Sample Calls
      5. The Design Specification—Conveying the Details of the Design
      6. Constructing a Design Specification
      7. Following Through on the Initial Design Phase
      8. Where We've Been—Where We're Going
    3. Writing Effective Prompts
      1. The Language of Asking Questions
      2. The Art of Writing Perfect Prompts
      3. Writing Prompts for Elegance, Speed, and Value
      4. Getting Callers to Focus on the Essentials
      5. Some Subtleties of Prompt Writing
      6. Top Five Good Tenets for Writing Prompts
      7. Top Five Mistakes When Writing Prompts
      8. Where We've Been—Where We're Going
    4. Production And Branding
      1. Notes About Implementation and Programming
      2. Production
      3. Prompt Creation—Text-to-Speech and Recorded Voices
      4. Casting
      5. Directing Voice Talents
      6. The Art of Recording Prompts
      7. Other Thoughts on Directing
      8. Concatenative Prompt Recording
      9. Some Metrics and Technical Notes
      10. Audio Icons
      11. Branding
      12. Where We've Been—Where We're Going
    5. Usability Testing
      1. The Value of Usability Testing
      2. How We Test an Application
      3. Objectives of Usability Testing
      4. Preparing for the Test
      5. The Test Subjects
      6. How to Get Test Subjects
      7. The Test Environment
      8. Types of Tests
      9. The Test Is Over—Now What?
      10. Interpreting Test Results
      11. Where We've Been—Where We're Going
    6. Deployment
      1. The Importance of Multi-Phase Deployment
      2. The Three Phases of Deployment
      3. Pilot Deployment
      4. Partial Deployment
      5. Full Deployment
      6. Where We've Been—Where We're Going
  6. Applied Knowledge
    1. Case Studies
      1. United Airlines: Shortcuts for Frequent Fliers
      2. United Airlines: Providing Extra Help For Those Who Need It
      3. Continental Airlines: A Different Approach to Flight Information
      4. A Top-Five Investment Management Company: Handling Complex Two-Choice Questions
      5. An Online Brokerage Firm: Managing More Complex Tasks
      6. An Online Brokerage Firm: Preferences and Other Rarely Used Functions
      7. A Regional Telephone Company: Dealing With Legal Notices and Disclaimers
      8. Wildfire: List Navigation
      9. Wildfire: Small Header, Large Body Lists
      10. A Top-Five U.S. Bank: Large Header, Small Body Lists
      11. The “Race Condition”
      12. FedEx: Scaffolding Prompts
      13. Amtrak: Implicit Confirmation and the “ellipses/and” Question Form
      14. AirTran: Reducing the Information Burden
      15. Guessing Right
      16. Semantics: When “Problem” Was a Problem
      17. Where We've Been—Where We Must Go
    2. Postscript
    3. Suggested Reading List
    4. Glossary