Understanding speech recognition has never been easier!
| |
| |
How to Build a Speech Recognition Application
| |
|
The Most Thorough, Practical, Step-by-Step Guide
Ever Written about speech recognition, by experts
who have been designing and developing
successful applications for years.
|
|
|
|
Who should read this book:
- Designers
- Developers
- Project Managers
- Marketing Managers
- Information Systems Managers
- Call Center Managers
And anyone else involved with
the implementation and management
of "self service" information delivery systems
|
Contents include how to:
- Craft effective prompts.
- Predict and manage social
user-behaviors.
- Reduce the application to a set
of repeatable speech behaviors.
- Keep a consistent "look and feel"
to the interface.
- Approach the problem of application "personality".
- Prevent and recover from errors.
- And much more...
|
About the Authors
Bruce Balentine has over fourteen years experience with the design and development of speech, audio, and multimodal user interfaces. As proprietor of Same Page Design Group, he provides research and interface design consulting services world-wide. He has held key positions with Voice Control Systems, Scott Instruments, and Future Computing. His expertise includes user interface design for telecommunications, desktop multimedia, entertainment, language training, medical, and home automation products.
Mr. Balentine earned a Bachelor’s and Master's Degree from the University of North Texas with interdisciplinary work in electronic music, computer music, and inter-media. Prior to specializing in speech, he devoted more than ten years to work in audio recording, photography, lighting, and other performance and production media. Mr. Balentine is also the author of "The GoodListener Cookbook," as well as several articles and publications related to spoken user interfaces.
David Morgan has over ten years experience with speech recognition and related voice technologies. As Vice President of Voice Systems Research for Fidelity Investments, he researches and helps design customer contact technologies for Fidelity's call centers, computer telephony systems, email, and web channels. Dr. Morgan’s previous work experience includes digital signal processing chip design, directory assistance systems, and voice and communications surveillance systems.
Dr. Morgan received his Ph.D. in Electrical Engineering from Brown University. He is also the author of "Neural Networks and Speech Processing." In addition, Dr. Morgan has published over twenty papers in the speech processing field and has taught a graduate course entitled, "Digital Signal Processing of Speech" at Northeastern University.
Click on titles below for a detailed list of each chapter:
|
CHAPTER 1 - THE TELEPHONY USER INTERFACE
- A Style Guide For User Interface
- Basic Speech Interface Concepts
- Terminology
- How This Book Is Organized
CHAPTER 2 - SPOKEN MACHINE OUTPUT
- Physical Properties of Machine Speech
- Properties of Spoken Output
- Prompts
- Feedback
- Instructions
- Help
- Application Data
CHAPTER 3 - SELECTING THE VOCABULARY
- The Recognizer’s Impact On Vocabulary Selection
- Consistency In Vocabulary Selection
CHAPTER 4 - BARGE-IN AND TURN TAKING
- Technical Discussion
- Choosing A Turn-Taking Protocol
- Implementing Full-Duplex Design
- Implementing Half-Duplex Designs
CHAPTER 5 - TONES
- Non-Speech Audio
- When To Use Tones
- Prompting Tones
- Feedback/Confirmation Tones
- Context Tones
CHAPTER 6 - DIALOGUE DESIGN
- Dialogue Models
- Menus
- Yes/No Queries
- Reusable Speech Behaviors
CHAPTER 7 - MIXED MODALITIES: SPEECH AND DTMF
- Switching Between Speech and DTMF
- Mixing Speech and DTMF
CHAPTER 8 - NATURAL LANGUAGE INTERFACES
- What Is Natural Language?
- Reaching Terminals In The Hierarchy
- NL Prompt Design
- NL Error Prevention and Recovery
CHAPTER 9 - PERSONIFIED INTERFACES
- Issues With Personification
- Choosing Personality Traits
- Interaction Styles (HANC Examples)
CHAPTER 10 - ERROR RECOVERY AND PREVENTION
- Detecting and Handling Errors
- User Initiated Error Recovery
- Machine Initiated Corroboration or Recovery
- Error Prevention
CHAPTER 11 - TESTING, LOGGING, AND REPORTING
- Usability Testing
- Logging And Reporting
- Summary
APPENDIX A - NL HARDWARE PROVISIONING
- Wizard Of Oz Testing
- Computing The Required Number Of Licenses
- Hardware Provisioning
- Other Issues To Consider
- The Consequences of Insufficient Provisioning
top 
|
