| |
| |
| Introduction | |
| |
| |
| |
| Why Develop Speech Applications for the Telephone? | |
| |
| |
| |
| Speaking and Listening Is Fundamental to Our Lives | |
| |
| |
| |
| Speaking and Listening to a Computer Is Natural and Convenient | |
| |
| |
| |
| When Speaking and Listening to a Computer May Be Inappropriate | |
| |
| |
| |
| Speech Applications Are Possible Today | |
| |
| |
| |
| Speech Application Challenges | |
| |
| |
| |
| What Can You Do with a Single Phone Call? | |
| |
| |
| |
| Voice Portal Applications and Services Help Callers | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| How Speech Applications Work | |
| |
| |
| |
| Why Do We Need VoiceXML to Create Speech Interfaces to Web Applications? | |
| |
| |
| |
| A Sample VoiceXML Document | |
| |
| |
| |
| The VoiceXML Architecture | |
| |
| |
| |
| The Philosophy of Speech User Interforces | |
| |
| |
| |
| Voice Access to HTML Legacy Documents | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Technologies for Speech Applications | |
| |
| |
| |
| Introduction to Speech Technologies | |
| |
| |
| |
| The Four Essential Technologies | |
| |
| |
| |
| Other Recognition Technologies | |
| |
| |
| |
| Language Interpretation Technologies | |
| |
| |
| |
| Generation Technologies | |
| |
| |
| |
| Production Technologies | |
| |
| |
| |
| Related Technologies | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Creating Speech Applications | |
| |
| |
| |
| Who's Who--The playbill for the Speech Application Development Team | |
| |
| |
| |
| Identify the Application | |
| |
| |
| |
| Develop the Business Model | |
| |
| |
| |
| Specify the Application | |
| |
| |
| |
| Choose the Right Technology | |
| |
| |
| |
| Develop the Application | |
| |
| |
| |
| Test the Application | |
| |
| |
| |
| Deploy and Monitor the Application | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Introduction to VoiceXML | |
| |
| |
| |
| XML | |
| |
| |
| |
| VoiceXML Genealogy | |
| |
| |
| |
| VoiceXML Language | |
| |
| |
| |
| Events and Event Handlers | |
| |
| |
| |
| Other Features of VoiceXML | |
| |
| |
| |
| Speech Grammars | |
| |
| |
| |
| Semantic Attachments | |
| |
| |
| |
| Speech Synthesis | |
| |
| |
| |
| Limitations of VoiceXML | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Making the Computer Talk | |
| |
| |
| |
| Select the Technology | |
| |
| |
| |
| Design the Persona | |
| |
| |
| |
| Design the Sound | |
| |
| |
| |
| Audio Formatting | |
| |
| |
| |
| Develop Training and Help Strategies | |
| |
| |
| |
| Select the Amount of Information to Present to the Caller | |
| |
| |
| |
| Allow the Caller to Barge-in | |
| |
| |
| |
| Improve Synthesized Speech | |
| |
| |
| |
| Improve Prerecorded Speech | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Making the Computer Listen | |
| |
| |
| |
| Audio Input Quality | |
| |
| |
| |
| Grammars | |
| |
| |
| |
| Inline Grammars | |
| |
| |
| |
| External Grammars | |
| |
| |
| |
| Built-in Grammars | |
| |
| |
| |
| Semantic Interpretation for Speech Recognition Grammars | |
| |
| |
| |
| Touchtone or Spoken Voice? | |
| |
| |
| |
| What Can the Caller Say? | |
| |
| |
| |
| Encourage the Caller to Speak | |
| |
| |
| |
| Speech Recognition Errors and Their Causes | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Application-Directed Styles and Dialog Documents | |
| |
| |
| |
| Introduction to Dialogs | |
| |
| |
| |
| Touchtone Menus | |
| |
| |
| |
| ASR Menus | |
| |
| |
| |
| Forms | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| User-Directed Styles and Dialog Documents | |
| |
| |
| |
| Command and Control | |
| |
| |
| |
| Query | |
| |
| |
| |
| Dictation | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Mixed-Initiative Dialogs | |
| |
| |
| |
| Mixed-initiative Dialogs | |
| |
| |
| |
| Barge-In | |
| |
| |
| |
| Alternative Utterances | |
| |
| |
| |
| Out-of-Sequence Data Entry | |
| |
| |
| |
| Prompt for Missing Parameters | |
| |
| |
| |
| Overlapping Grammar Resolution | |
| |
| |
| |
| Single Utterance for Multiple Fields | |
| |
| |
| |
| Task Switching | |
| |
| |
| |
| Guidelines | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Testing--Tuning and Monitoring | |
| |
| |
| |
| Caller Classifications | |
| |
| |
| |
| Testing | |
| |
| |
| |
| Evaluate the Initial Dialog Designs | |
| |
| |
| |
| Evaluate the Components | |
| |
| |
| |
| Evaluate the Application Functions and Content | |
| |
| |
| |
| Stress-testing a Voice Application | |
| |
| |
| |
| Qualifying a Voice Application | |
| |
| |
| |
| Conducting Field Tests | |
| |
| |
| |
| Continuous Monitoring after Deployment | |
| |
| |
| |
| Support for Collecting Preference Data | |
| |
| |
| |
| Support for Collecting Performance Data | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Development Tools and Reusability | |
| |
| |
| |
| Development Tools | |
| |
| |
| |
| Audio Files | |
| |
| |
| |
| Grammars | |
| |
| |
| |
| Subdialogs | |
| |
| |
| |
| Objects | |
| |
| |
| |
| Applications and Services | |
| |
| |
| |
| Reusability Standards | |
| |
| |
| |
| Avoiding the Speech Winter | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Exercises and Projects | |
| |
| |
| |
| Multimodal Dialogs | |
| |
| |
| |
| Convergence of Cell Phones and Handheld Computers | |
| |
| |
| |
| Modes of Information Entry | |
| |
| |
| |
| Modes of Information Presentation | |
| |
| |
| |
| Architectures for Multimodal Dialogs | |
| |
| |
| |
| Requirements for Multimodal Dialogs | |
| |
| |
| |
| Extending VoiceXML for Multimedia and Multimodal Applications | |
| |
| |
| |
| Speech Tags | |
| |
| |
| |
| Comparison of Extended VoiceXML and Embedded Speech Tags | |
| |
| |
| |
| Key Concepts | |
| |
| |
| |
| Ajax Fast Foods Case Study | |
| |
| |
| Identify the Application | |
| |
| |
| Specify the Application | |
| |
| |
| Wizard of Oz Tests | |
| |
| |
| More User Testing | |
| |
| |
| Reusable Object | |
| |
| |
| In-House or Outsource Voice Portal Service | |
| |
| |
| |
| The W3C Speech Interface Framework | |
| |
| |
| Glossary | |
| |
| |
| Index | |