Muutke küpsiste eelistusi

E-raamat: Practical Speech User Interface Design [Taylor & Francis e-raamat]

  • Formaat: 344 pages, 50 Tables, black and white; 36 Illustrations, black and white
  • Sari: Human Factors and Ergonomics
  • Ilmumisaeg: 10-Dec-2010
  • Kirjastus: CRC Press Inc
  • ISBN-13: 9780429093623
Teised raamatud teemal:
  • Taylor & Francis e-raamat
  • Hind: 170,80 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 244,00 €
  • Säästad 30%
  • Formaat: 344 pages, 50 Tables, black and white; 36 Illustrations, black and white
  • Sari: Human Factors and Ergonomics
  • Ilmumisaeg: 10-Dec-2010
  • Kirjastus: CRC Press Inc
  • ISBN-13: 9780429093623
Teised raamatud teemal:
Although speech is the most natural form of communication between humans, most people find using speech to communicate with machines anything but natural. Drawing from psychology, human-computer interaction, linguistics, and communication theory, Practical Speech User Interface Design provides a comprehensive yet concise survey of practical speech user interface (SUI) design. It offers practice-based and research-based guidance on how to design effective, efficient, and pleasant speech applications that people can really use.

Focusing on the design of speech user interfaces for IVR applications, the book covers speech technologies including speech recognition and production, ten key concepts in human language and communication, and a survey of self-service technologies. The author, a leading human factors engineer with extensive experience in research, innovation and design of products with speech interfaces that are used worldwide, covers both high- and low-level decisions and includes Voice XML code examples. To help articulate the rationale behind various SUI design guidelines, he includes a number of detailed discussions of the applicable research.

The techniques for designing usable SUIs are not obvious, and to be effective, must be informed by a combination of critically interpreted scientific research and leading design practices. The blend of scholarship and practical experience found in this book establishes research-based leading practices for the design of usable speech user interfaces for interactive voice response applications.
Foreword xi
Preface xiii
Acknowledgments xv
The Author xvii
1 Introduction 1(6)
Foundations of Speech User Interface Design
1(1)
A Focus on Research-Based Design Guidance
2(1)
Organization of this Book
3(1)
Summary
4(1)
References
4(3)
2 Speech Technologies 7(20)
Speech Recognition
7(11)
Finite State Grammars
8(3)
VoiceXML
11(3)
Statistical Language Models
14(1)
Statistical Action Classification
14(1)
Statistical Parsing
15(1)
Dialog Management
16(1)
Confidence and N-Best Lists
17(1)
Detection of Emotion
17(1)
Speech Production
18(3)
Formant Text-to-Speech
18(1)
Concatenative Text-to-Speech
19(1)
Expressive Speech Production
19(1)
The Components of Satisfaction with Speech Output
20(1)
Recorded Speech Segments
20(1)
Speech Biometrics
21(1)
Summary
22(1)
References
23(4)
3 Key Concepts in Human Language and Communication 27(22)
Implicit Linguistic Knowledge
27(1)
Phonology
28(1)
Coarticulation
29(2)
Prosody
31(1)
Conversational Discourse
32(2)
Conversational Maxims
34(2)
Grammaticality
36(2)
Discourse Markers
38(2)
Timing and Turntaking
40(1)
Social Considerations in Conversation
41(3)
Summary
44(1)
References
45(4)
4 Self-Service Technologies 49(32)
Service Science
49(2)
Call Centers
51(2)
Technology Acceptance and Readiness
53(4)
Satisfaction with and Adoption of SSTs
57(3)
Relationship of IVR to Other SSTs
60(2)
Waiting for Service
62(9)
Service Recovery
71(2)
Consequences of Forced Use of SSTs
73(1)
Summary
74(2)
References
76(5)
5 The Importance of Speech User Interface Design 81(12)
User Acceptance of Speech IVR Applications
81(4)
Market Research
81(2)
Agent and Channel Costs
83(1)
Scientific Research
84(1)
Location on the "Hype Cycle"
85(2)
The Disciplines of SUI Design and the SUI Design Team
87(1)
The Consumers of SUI Design
88(1)
Major SUI Objectives
89(1)
The Components of SUI Usability
89(1)
The Power of the SUI
90(1)
Summary
90(1)
References
91(2)
6 Speech User Interface Development Methodology 93(76)
Concept Phase
94(1)
Requirements Phase
94(8)
Analyzing Users
94(5)
Analyzing User Tasks
99(3)
Design Phase
102(4)
Developing the Conceptual Design
103(1)
Making High-Level Decisions
104(1)
Making Low-Level Decisions
104(1)
Defining the High-Level Call Flow
104(1)
Creating the Detailed Dialog Specification
105(1)
Prototyping
105(1)
Development Phase
106(1)
Test Phase
107(12)
System Verification and Customer Acceptance Tests
107(1)
Grammar Testing
107(5)
Dealing with Recognition Problems
112(1)
Usability Testing
113(4)
Automated SUI Usability Testing Methods
117(2)
Deployment Phase
119(1)
Tuning Phase
119(3)
Surveys
120(1)
Call Log Analysis
120(2)
End-to-End Call Monitoring
122(1)
Sample Design Documents
122(37)
High-Level Call Flow
123(1)
Detailed Dialog Specification (DDS)
124(33)
Scenarios Derived from Detailed Dialog Specification
157(1)
Recording Manifest
157(1)
Availability of Sample Design Documents
158(1)
Summary
159(4)
References
163(6)
7 Getting Started: High-Level Design Decisions 169(32)
Choosing the Barge-In Style
169(2)
Lombard Speech and the "Stuttering Effect"
170(1)
Comparing Barge-In Detection Methods
170(1)
Selecting Recorded Prompts or Synthesized Speech
171(6)
Creating Recorded Prompts
171(2)
Using TTS Prompts
173(4)
SUI Personality and Persona
177(3)
Deciding Whether to Use Audio Formatting
180(1)
Using Simple or Complex Speech Recognition
181(3)
Evaluating the Need for Complex Speech Recognition
182(1)
Flattening Menus
182(1)
Flattening Forms
183(1)
Adopting a Concise or Verbose Prompt Style
184(1)
Allowing Only Speech Input or Speech plus Touchtone
185(1)
Choosing a Set of Global Navigation Commands
186(4)
Go Back
187(1)
Exit
188(1)
Using the Global Commands
189(1)
Deciding Whether to Use Human Agents in the Deployed System
190(3)
Designing for In-Hours and After-Hours Operation
191(1)
Managing Early Requests for and Transfers to an Agent
191(2)
Choosing a Help Mode or Self-Revealing Contextual Help
193(2)
Maximizing the Benefits of Self-Revealing Contextual Help
193(1)
Implementing Self-Revealing Contextual Help
193(1)
Bailing Out
194(1)
Summary
195(1)
References
196(5)
8 Getting Specific: Low-Level Design Decisions 201(68)
Creating Introductions
201(5)
Welcome (Required)
202(1)
Language Selection (Optional)
203(1)
Purpose (Optional)
204(1)
Short List of Global Commands (Optional)
204(1)
Interrupt at Any Time (Optional)
204(1)
Let's Get Started (Optional)
205(1)
Initial Prompt (Required)
205(1)
Putting It All Together
205(1)
Avoiding Poor Practices in Introductions
206(3)
Web Deflection Messages
206(1)
Sales Pitches
207(1)
Prompts for Touchtone versus Speech
208(1)
Your Call Is Important to Us
208(1)
Please Listen Carefully as Our Options Have Changed
208(1)
This Call May Be Monitored or Recorded
209(1)
Getting the Right Timing
209(12)
Research on Turntaking Behaviors in Speech Recognition IVRs
210(1)
Setting the Noinput Timeout Value
211(1)
Timing Pauses between Menu Items
212(3)
Timing Pauses between Prompts and Prompt Extensions
215(4)
Managing Processing Time
219(2)
Designing Dialogs
221(10)
Writing Directive Prompts
222(1)
Making Nondirective Prompts Usable
223(5)
Mixed-Mode Prompting
228(2)
"Press or Say <X>" Prompting
230(1)
Constructing Appropriate Menus and Prompts
231(16)
Optimal Menu Length
232(8)
Grouping Menu Items
240(1)
Minimizing Error Declarations
240(1)
Avoiding Touchtone-Style Prompts
241(1)
Choosing a Complex Alternative
241(1)
Crafting Effective Prompts
242(2)
Managing Digressions
244(2)
Stepping Stones and Safety Nets
246(1)
Tips for Voice Spelling
247(4)
Confirming User Input
251(9)
Implicit Confirmation
252(1)
Explicit Confirmation
253(1)
Immediate Explicit Confirmation: Separate Dialog Turns
254(1)
Skip Lists
254(1)
Delayed (Batch) Explicit Confirmation: Basic
254(1)
Delayed (Batch) Explicit Confirmation: Improved
255(2)
Comparison of Confirmation Strategies
257(1)
Refining Confirmation and Error Correction with Confidence Levels and N-Best Lists
258(2)
Summary
260(2)
References
262(7)
9 From "Hello World" to "The Planets": Prototyping SUI Designs with VoiceXML 269(46)
Sample 1: Hello World'
270(1)
Some VoiceXML Concepts
270(1)
Sample 2: Hello Worlds
271(3)
Sample
3. Adding More Complex Features to Hello Worlds
274(9)
Playing an Introduction Once
274(4)
Defining Always-Active Commands with Links
278(1)
Using Grammar Tags to Classify Responses
279(1)
Setting Variables to Document-Level Scope
280(1)
Directing the Call Flow with If Statements in the Filled Section
281(1)
Using the Document-Level Variables and Unconditional Return to the Main Menu
281(1)
Exiting without Confirmation
282(1)
Sample
4. Even More Features
283(27)
Creating Self-Revealing Help
283(1)
Defining an Unconditional Go Back
284(2)
Defining a Conditional Go Back
286(1)
Exiting with Confirmation
286(3)
Integrating Audio Tones
289(1)
Simulating Data Acquisition from a Backend Server
289(1)
Playing the Data
290(2)
Using Breaks to Fine Tune Timing
292(18)
Using Recorded Speech
310(2)
Replacing TTS with Recorded Speech
310(1)
Editing Recorded Audio Segments
310(1)
Dynamic Selection of Audio Segments
310(2)
Using an Application Root Document
312(1)
Summary
312(1)
References
313(2)
10 Final Words 315(4)
I Appreciate Your Patience
315(1)
Please Hold for the Next Available Research
315(2)
Thanks for Reading, Goodbye!
317(2)
Index 319
James R. Lewis is a Senior Human Factors Engineer with IBM Software Group in Delray Beach, Florida.