Gardner-Bonneau / Blanchard Human Factors and Voice Interactive Systems

2. Auflage 2008
ISBN: 978-0-387-68439-0
Verlag: Springer US
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 469 Seiten

Reihe: Signals and Communication Technology

The second edition of Human Factors and Voice Interactive Systems, in addition to updating chapters from the first edition, adds in-depth information on current topics of major interest to speech application developers. These topics include use of speech technologies in automobiles, speech in mobile phones, natural language dialogue issues in speech application design, and the human factors design, testing, and evaluation of interactive voice response (IVR) applications.

Autoren/Hrsg.

Gardner-Bonneau, Daryle

Blanchard, Harry E.

Inhaltsverzeichnis

1;PREFACE;7
1.1;REFERENCES;13
2;ACKNOWLEDGEMENTS;15
3;Chapter 1 IVR USABILITY ENGINEERING USING GUIDELINES AND ANALYSES OF END- TO- END CALLS;26
3.1;1. IVR DESIGN PRINCIPLES AND GUIDELINES;27
3.1.1;1.1 A Taxonomy of Limitations of Speech User Interfaces;28
3.1.2;1.2 Towards Best Practices for IVR Design;35
3.1.3;1.3 Best Practices for IVR Design?;43
3.2;2. DATA-DRIVEN IVR USABILITY ENGINEERING BASED ON END- TO- END CALLS;44
3.2.1;2.1 The Flaws of Standard IVR Reports;45
3.2.2;2.2 Capturing End-to-End Data from Calls;45
3.2.3;2.3 Evaluating IVR Usability based on End-to-End Calls;48
3.2.4;2.4 Evaluating IVR Cost-effectiveness;54
3.3;3. SUMMARY AND CONCLUSIONS;62
3.4;ACKNOWLEDGEMENTS;64
3.5;REFERENCES;64
4;Chapter 2 User Interface Design for Natural Language Systems: From Research to Reality;67
4.1;1. INTRODUCTION ;67
4.1.1;1.1 What is Natural Language?;67
4.1.2;1.2 What Are the Steps to Building a Natural Language Application?;70
4.1.3;1.3 When Does it Make Sense to Use Natural Language?;74
4.1.4;1.4 The Call Routing Task;78
4.1.5;1.5 Design Process;78
4.1.6;1.6 Analysis of Human-to-Human Dialogues;79
4.2;2. ANTHROPOMORPHISM AND USER EXPECTATIONS;79
4.2.1;2.1 Anthropomorphism Experiment;80
4.3;3. ISSUES FOR NATURAL DIALOGUE DESIGN;84
4.3.1;3.1 Initial Greeting;84
4.3.2;3.2 Confirmations;84
4.3.3;3.3 Disambiguating an Utterance;85
4.3.4;3.4 Reprompts;85
4.3.5;3.5 Turn-taking;86
4.3.6;3.6 When to Bail Out;86
4.4;4. ESTABLISHING USER EXPECTATIONS IN THE INITIAL GREETING;86
4.4.1;4.1 Initial Greeting Experiment;87
4.5;5. IDENTIFYING RECOGNITION ERRORS THROUGH CONFIRMATIONS;90
4.5.1;5.1 Confirming Digit Strings in Spoken Dialogue Systems;91
4.5.2;5.2 Confirmation of Topic in a Spoken Natural Dialogue System;93
4.6;6. REPAIRING RECOGNITION ERRORS WITH REPROMPTS;96
4.6.1;6.1 Reprompt Experiment;97
4.7;7. TURN-TAKING IN HUMAN-MACHINE DIALOGUES;100
4.7.1;7.1 Caller Tolerance of System Delay;101
4.8;8. SUMMARY;103
4.9;REFERENCES;103
5;Chapter 3 LINGUISTICS AND PSYCHOLINGUISTICS IN IVR DESIGN;105
5.1;1. INTRODUCTION;106
5.1.1;1.1 Speech Sounds;106
5.1.2;1.2 Grammar;107
5.2;2. ASR GRAMMARS AND LANGUAGE UNDERSTANDING;110
5.2.1;2.1 Morphology;111
5.2.2;2.2 Syntax;112
5.2.3;2.3 Semantics;117
5.2.4;2.4 Putting it All Together;118
5.2.5;2.5 ASR Grammars;119
5.2.6;2.6 Natural Language Understanding Models;121
5.3;3. DIALOG DESIGN;126
5.3.1;3.1 Putting it All Together;129
5.4;4. CONSEQUENCES OF STRUCTURAL SIMPLIFICATION;132
5.4.1;4.1 Semantic Specificity;135
5.4.2;4.2 Syntactic Specificity;136
5.5;CONCLUSION;137
5.6;REFERENCES;137
6;Chapter 4 DESIGNING THE VOICE USER INTERFACE FOR AUTOMATED DIRECTORY ASSISTANCE;140
6.1;1. THE BUSINESS OF DA;140
6.1.1;1.1 The Introduction of Automation;141
6.1.2;1.2 Early Attempts to Use Speech Recognition;142
6.2;2. ISSUES IN THE DESIGN OF VUI FOR DA;144
6.2.1;2.1 Addressing Database Inadequacies;145
6.2.2;2.2 Pronunciation of Names;146
6.2.3;2.3 The First Question;147
6.2.4;2.4 Finding the Locality;147
6.2.5;2.5 Confirming the Locality;148
6.2.6;2.6 Determining the Listing Type;149
6.2.7;2.7 Handling Business Requests;150
6.2.8;2.8 Handling Residential Listings;154
6.2.9;2.9 General Dialogue Design Issues;156
6.3;3. FINAL THOUGHTS;157
6.4;REFERENCES;157
7;Chapter 5 SPOKEN LANGUAGE INTERFACES FOR EMBEDDED APPLICATIONS;158
7.1;1. INTRODUCTION;158
7.2;2. SPOKEN LANGUAGE INTERFACES DEVELOPMENT ;160
7.2.1;2.1 Overview. Current Trends;160
7.2.2;2.2 Embedded Speech Applications;162
7.3;3. EMBEDDED SPEECH TECHNOLOGIES;164
7.3.1;3.1 Technical Constraints and Implementation Methods;164
7.3.2;3.2 Embedded Speech Recognition;166
7.3.3;3.3 Embedded Speech Synthesis;172
7.4;4. A CASE STUDY: AN EMBEDDED TTS SYSTEM IMPLEMENTATION ;176
7.4.1;4.1 A Simplified TTS System Architecture;176
7.4.2;4.2 Implementation Issues;178
7.5;5. THE FUTURE OF EMBEDDED SPEECH INTERFACES;181
7.6;REFERENCES;183
8;Chapter 6 SPEECH GENERATION IN MOBILE PHONES;185
8.1;1. INTRODUCTION;185
8.2;2. SPEAKING TELEPHONE? WHAT IS IT GOOD FOR?;187
8.3;3. SPEECH GENERATION TECHNOLOGIES IN MOBILE PHONES;188
8.3.1;3.1 Synthesis Technologies;189
8.3.2;3.2 Topic-Related Text Preprocessing;192
8.4;4. HOW TO PORT SPEECH SYNTHESIS ON A PHONE PLATFORM;200
8.5;5. LIMITATIONS AND POSSIBILITIES OFFERED BY PHONE RESOURCES;203
8.6;6. IMPLEMENTATIONS;205
8.6.1;6.1 The Mobile Phone as a Speaking Aid;205
8.6.2;6.2 An SMS-Reading Mobile Phone Application;208
8.7;ACKNOWLEDGEMENTS;212
8.8;REFERENCES;212
9;Chapter 7 VOICE MESSAGING USER INTERFACE;214
9.1;1. INTRODUCTION;214
9.2;2. THE TOUCH-TONE VOICE MAIL USER INTERFACE;217
9.2.1;2.1 Common Elements of Touch-tone Transactions;218
9.2.2;2.2 Call Answering;224
9.2.3;2.3 The Subscriber Interface;227
9.2.4;2.4 Retrieving and Manipulating Messages;227
9.2.5;2.5 Sending Messages;230
9.2.6;2.6 Voice Messaging User Interface Standards;232
9.2.7;2.7 Alternative Approaches to Traditional Touch-tone Design;235
9.3;3. AUTOMATIC SPEECH RECOGNITION AND VOICE MAIL;236
9.4;4. UNIFIED MESSAGING AND MULTIMEDIA MAIL;240
9.4.1;4.1 Fax Messaging;241
9.4.2;4.2 Viewing Voice Mail;242
9.4.3;4.3 Listening to E-mail;244
9.4.4;4.4 Putting it All Together;245
9.4.5;4.5 Mixed Media;246
9.5;REFERENCES;247
10;Chapter 8 SILENCE LOCATIONS AND DURATIONS IN DIALOG MANAGEMENT;251
10.1;1. INTRODUCTION;251
10.2;2. PROMPTS AND RESPONSES IN DIALOG MANAGEMENT;253
10.2.1;2.1 Dialog Management;253
10.2.2;2.2 Word Selection;254
10.2.3;2.3 Word Lists;254
10.2.4;2.4 Turn-Taking Cues;256
10.3;3. TIME AS AN INDEPENDENT VARIABLE – DIALOG MODEL;256
10.3.1;3.1 Definition of Terms;257
10.3.2;3.2 Examples of Usage;258
10.4;4. USER BEHAVIOR ;258
10.4.1;4.1 Transactional Analysis;258
10.4.2;4.2 Verbal Communication;259
10.4.3;4.3 Directed Dialogs;259
10.5;5. MEASUREMENTS;260
10.5.1;5.1 Barge-In;261
10.6;6. USABILITY TESTING AND RESULTS;262
10.6.1;6.1 Test Results – United States (early prototype);264
10.6.2;6.2 Test Results – United States (tuned, early prototype);265
10.6.3;6.3 Test Results – United Kingdom;266
10.6.4;6.4 Test Results – Italy;267
10.6.5;6.5 Test Results – Denmark;269
10.7;7. OBSERVATIONS AND INTERPRETATIONS ;270
10.7.1;7.1 Lateral Results;270
10.7.2;7.2 Learning – Longitudinal Results;271
10.8;CONCLUSIONS;272
10.9;ACKNOWLEDGEMENT;272
10.10;REFERENCES;272
11;Chapter 9 USING NATURAL DIALOGS AS THE BASIS FOR SPEECH INTERFACE DESIGN;274
11.1;1. INTRODUCTION;275
11.1.1;1.1 Motivation;275
11.1.2;1.2 Natural Dialog Studies;276
11.2;2. NATURAL DIALOG CASE STUDIES;277
11.2.1;2.1 Study #1: SpeechActs Calendar (speech-only, telephone- based);278
11.2.2;2.2 Study #2: Office Monitor (speech-only, microphone-based);283
11.2.3;2.3 Study #3: Automated Customer Service Representative ( speech input, speech/ graphical output, telephone- based);288
11.2.4;2.4 Study #4: Multimodal Drawing ( speech/ mouse/ keyboard input, speech/graphical output, microphone- based);297
11.3;3. DISCUSSION;305
11.3.1;3.1 Refining Application Requirements and Functionality;305
11.3.2;3.2 Collecting Appropriate Vocabulary;306
11.3.3;3.3 Determining Commonly Used Grammatical Constructs;306
11.3.4;3.4 Discovering Effective Interaction Patterns;306
11.3.5;3.5 Helping with Prompt and Feedback Design;307
11.3.6;3.6 Getting a Feeling for the Tone of the Conversations;307
11.4;CONCLUSION;308
11.5;ACKNOWLEDGEMENTS;308
11.6;REFERENCES;309
12;Chapter 10 TELEMATICS: ARTIFICIAL PASSENGER AND BEYOND;310
12.1;1. INTRODUCTION;310
12.2;2. A BRIEF OVERVIEW OF IBM VOICE TECHNOLOGIES;311
12.2.1;2.1 Conversational Interactivity for Telematics;312
12.2.2;2.2 System Architecture;314
12.2.3;2.3 Embedded Speech Recognition;316
12.2.4;2.4 Distributed Speech Recognition;318
12.3;3. EVALUATING/PREDICTING THE CONSEQUENCES OF MISRECOGNITIONS;319
12.4;4. IMPROVING VOICE AND STATE RECOGNITION PERFORMANCE – NETWORK DATA COLLECTION, LEARNING BY EXAMPLE, ADAPTATION OF LANGUAGE AND ACOUSTIC MODELS FOR SIMILAR USERS;322
12.5;5. ARTIFICIAL PASSENGER;327
12.6;6. USER MODELING ASPECTS;334
12.6.1;6.1 User Model;335
12.6.2;6.2 The Adaptive Modeling Process;336
12.6.3;6.3 The Control Process;337
12.6.4;6.4 Discussion about Time- Lagged Observables and Indicators in a History;338
12.7;7. GESTURE-BASED COMMAND INTERFACE;339
12.8;8. SUMMARY;341
12.9;ACKNOWLEDGEMENTS;342
12.10;REFERENCES;342
13;Chapter 11 A LANGUAGE TO WRITE LETTER-TO-SOUND RULES FOR ENGLISH AND FRENCH;345
13.1;1. INTRODUCTION;345
13.2;2. THE HISTORIC EVOLUTION OF ENGLISH A N D FRENCH;347
13.3;3. THE COMPLEXITY OF THE CONVERSION FOR ENGLISH AND FRENCH;347
13.4;4. RULE FORMALISM;352
13.5;5. EXAMPLES OF RULES FOR ENGLISH;358
13.6;6. EXAMPLES OF RULES FOR FRENCH;363
13.7;CONCLUSIONS;371
13.8;REFERENCES;372
13.9;APPENDICES FOR FRENCH;374
13.10;APPENDICES FOR ENGLISH;377
14;Chapter 12 VIRTUAL SENTENCES OF SPONTANEOUS SPEECH: BOUNDARY EFFECTS OF SYNTACTIC-SEMANTIC-PROSODIC PROPERTIES;379
14.1;1. INTRODUCTION;379
14.2;2. METHOD AND MATERIAL ;382
14.2.1;2.1 Subjects;382
14.2.2;2.2 Speech Material;382
14.2.3;2.3 Procedure;383
14.3;3. RESULTS;384
14.3.1;3.1 Identification of Virtual Sentences in the Normal and Filtered Speech Samples;384
14.3.2;3.2 Pauses of the speech sample;386
14.3.3;3.3 Pause Perception;388
14.3.4;3.4 F0 Patterns;390
14.3.5;3.5 Comprehension of the Spontaneous Speech Sample;392
14.3.6;3.6 The Factor of Gender;393
14.4;Conclusions;393
14.5;ACKNOWLEDGEMENTS;395
14.6;REFERENCES;395
15;Chapter 13 TEXT-TO-SPEECH FORMANT SYNTHESIS FOR FRENCH;398
15.1;1. INTRODUCTION;398
15.2;2. GRAPHEME-TO-PHONEME CONVERSION;399
15.2.1;2.1 Normalization: From Grapheme to Grapheme;399
15.2.2;2.2 From Grapheme to Phoneme;401
15.2.3;2.3 Exception Dictionary;402
15.3;3. PROSODY ;402
15.3.1;3.1 Parsing the Text;402
15.3.2;3.2 Intonation;403
15.3.3;3.3 Phoneme Duration;408
15.4;4. ACOUSTICS FOR FRENCH CONSONANTS AND VOWELS;415
15.4.1;4.1 Vowels;415
15.4.2;4.2 Fricatives (unvoiced:F,S,Ch; voiced: V,Z,J);417
15.4.3;4.3 Plosives (unvoiced:P,T,K; voiced: B,D,G);418
15.4.4;4.4 Nasals (M, N, Gn, Ng);420
15.4.5;4.5 Liquids (L, R);421
15.4.6;4.6 Semivowels (Y, W, Wu);422
15.4.7;4.7. Phoneme Transitions (coarticulation effects);422
15.4.8;4.8 Frame Generation;426
15.4.9;4.9 Conclusions for acoustics;426
15.5;5. FROM ACOUSTICS TO SPEECH SIGNAL;427
15.6;6. NEXT GENERATION FORMANT SYNTHESIS;429
15.7;7. SINGING;431
15.8;CONCLUSIONS;431
15.9;REFERENCES;432
16;Chapter 14 ACCESSIBILITY AND SPEECH TECHNOLOGY: ADVANCING TOWARD UNIVERSAL ACCESS;434
16.1;1. UNIVERSAL ACCESS VS. ASSISTIVE TECHNOLOGY;434
16.2;2. PREDICTED ENHANCEMENTS AND IMPROVEMENTS TO UNDERLYING TECHNOLOGY ;436
16.2.1;2.1 Social Network Analysis, Blogs, Wikis, and Social Computing;437
16.2.2;2.2 Intelligent Agents;438
16.2.3;2.3 Learning Objects;439
16.2.4;2.4 Cognitive Aids;440
16.2.5;2.5 Interface Flexibility and Intelligence;440
16.3;3. CURRENT ASSISTIVE TECHNOLOGY APPLICATIONS EMPLOYING SPEECH TECHNOLOGY;440
16.3.1;3.1 Applications Employing Automatic Speech Recognition ( ASR);441
16.3.2;3.2 Applications of Synthetic Speech;445
16.4;4. HUMAN-COMPUTER INTERACTION: DESIGN AND EVALUATION;447
16.5;5. THE ROLE OF TECHNICAL STANDARDS IN ACCESSIBILITY;450
16.5.1;5.1 Standards Related to Software and Information Technology User Interfaces;451
16.5.2;5.2 Speech Application Accessibility Standards;451
16.5.3;5.3 Accessibility Data and Accessibility Guidance for General Products;454
16.6;CONCLUSIONS;456
16.7;REFERENCES;457
17;Chapter 15 SYNTHESIZED SPEECH USED FOR THE EVALUATION OF CHILDREN’S HEARING AND SPEECH PERCEPTION;460
17.1;1. INTRODUCTION;460
17.2;2. THE BACKGROUND THEORY;461
17.3;3. THE PRODUCTION OF THE SYNTHESIZED WORD MATERIAL;464
17.4;4. PRE-EXPERIMENTS FOR THE APPLICATION OF SYNTHESIZED WORDS FOR HEARING SCREENING;466
17.5;5. RESULTS ;467
17.5.1;5.1 Clinical Tests;467
17.5.2;5.2 Screening Procedure;470
17.5.3;5.3 Evaluation of Acoustic-phonetic Perception;473
17.5.4;5.4 Children with Specific Needs;474
17.6;CONCLUSIONS;475
17.7;ACKNOWLEDGEMENTS;476
17.8;REFERENCES;476
18;INDEX;477