Handling Emotions in Human-Computer Dialogues (eBook)
X, 276 Seiten
Springer Netherlands (Verlag)
978-90-481-3129-7 (ISBN)
In this book, a novel approach that combines speech-based emotion recognition with adaptive human-computer dialogue modeling is described. With the robust recognition of emotions from speech signals as their goal, the authors analyze the effectiveness of using a plain emotion recognizer, a speech-emotion recognizer combining speech and emotion recognition, and multiple speech-emotion recognizers at the same time. The semi-stochastic dialogue model employed relates user emotion management to the corresponding dialogue interaction history and allows the device to adapt itself to the context, including altering the stylistic realization of its speech. This comprehensive volume begins by introducing spoken language dialogue systems and providing an overview of human emotions, theories, categorization and emotional speech. It moves on to cover the adaptive semi-stochastic dialogue model and the basic concepts of speech-emotion recognition. Finally, the authors show how speech-emotion recognizers can be optimized, and how an adaptive dialogue manager can be implemented. The book, with its novel methods to perform robust speech-based emotion recognition at low complexity, will be of interest to a variety of readers involved in human-computer interaction.
In this book, a novel approach that combines speech-based emotion recognition with adaptive human-computer dialogue modeling is described. With the robust recognition of emotions from speech signals as their goal, the authors analyze the effectiveness of using a plain emotion recognizer, a speech-emotion recognizer combining speech and emotion recognition, and multiple speech-emotion recognizers at the same time. The semi-stochastic dialogue model employed relates user emotion management to the corresponding dialogue interaction history and allows the device to adapt itself to the context, including altering the stylistic realization of its speech. This comprehensive volume begins by introducing spoken language dialogue systems and providing an overview of human emotions, theories, categorization and emotional speech. It moves on to cover the adaptive semi-stochastic dialogue model and the basic concepts of speech-emotion recognition. Finally, the authors show how speech-emotion recognizers can be optimized, and how an adaptive dialogue manager can be implemented. The book, with its novel methods to perform robust speech-based emotion recognition at low complexity, will be of interest to a variety of readers involved in human-computer interaction.
Preface 5
Contents 8
1 Introduction 10
1.1 Spoken Language Dialogue Systems 11
1.1.1 Automatic Speech Recognition 11
1.1.2 Natural Language Understanding 12
1.1.3 Dialogue Management 13
1.1.4 Text Generation 14
1.1.5 Text-to-Speech 14
1.2 Enhancing a Spoken Language Dialogue System 15
1.3 Challenges in Dialogue Management Development 17
1.4 Issues in User Modeling 20
1.5 Evaluation of Dialogue Systems 23
1.6 Summary of Contributions 25
2 Human Emotions 28
2.1 Definition of Emotion 28
2.2 Theories of Emotion and Categorization 31
2.3 Emotional Labeling 45
2.4 Emotional Speech Databases/Corpora 51
2.5 Discussion 54
3 Adaptive Human–Computer Dialogue 55
3.1 Background and Related Research 56
3.1.1 Adaptive Dialogue Management 56
3.1.2 Stochastic Approaches to Dialogue Modeling 64
3.1.3 Emotions in Dialogue Systems 67
3.2 User-State and Situation Management 69
3.3 Dialogue Strategies and Control Parameters 73
3.4 Integrating Speech Recognizer Confidence Measures into Adaptive Dialogue Management 74
3.5 Integrating Emotions into Adaptive Dialogue Management 80
3.6 A Semi-Stochastic Dialogue Model 86
3.7 A Semi-Stochastic Emotional Model 98
3.8 A Semi-Stochastic Combined Emotional Dialogue Model 103
3.9 Extending the Semi-Stochastic Combined Emotional Dialogue Model 108
3.10 Discussion 112
4 Hybrid Approach to Speech–Emotion Recognition 114
4.1 Signal Processing 115
4.1.1 Preprocessing 117
4.1.2 Linear Prediction 119
4.1.3 Mel-Frequency Cepstral Coefficients 119
4.1.4 Prosodic and Acoustic Features 120
4.2 Classifiers for Emotion Recognition 127
4.2.1 Hidden Markov Models 128
4.2.2 Artificial Neural Networks 132
4.3 Existing Approaches to Emotion Recognition 134
4.4 HMM-Based Speech Recognition 138
4.5 HMM-Based Emotion Recognition 142
4.6 Combined Speech and Emotion Recognition 149
4.7 Emotion Recognition by Linguistic Analysis 151
4.8 Discussion 156
5 Implementation 157
5.1 Emotion Recognizer Optimizations 157
5.1.1 Plain Emotion Recognition 158
5.1.2 Speech–Emotion Recognition 161
5.2 Using Multiple (Speech–)Emotion Recognizers 165
5.2.1 ROVER for Emotion Recognition 172
5.2.2 ROVER for Speech–Emotion Recognition 176
5.3 Implementation of Our Dialogue Manager 179
5.4 Discussion 191
6 Evaluation 192
6.1 Description of Dialogue System Evaluation Paradigms 192
6.2 Speech Data Used for the Emotion Recognizer Evaluation 195
6.3 Performance of Our Emotion Recognizer 197
6.3.1 Plain Emotion Recognition 203
6.3.2 Speech–Emotion Recognition 207
6.3.3 Combining Multiple Speech–Emotion Recognizers 216
6.3.4 Emotion Recognition by Linguistic Analysis 220
6.4 Evaluation of Our Dialogue Manager 222
6.5 Discussion 228
7 Conclusion and Future Directions 231
A Emotional Speech Databases 240
B Used Abbreviations 254
References 256
Index 276
| Erscheint lt. Verlag | 28.10.2009 |
|---|---|
| Zusatzinfo | X, 276 p. |
| Verlagsort | Dordrecht |
| Sprache | englisch |
| Themenwelt | Geisteswissenschaften ► Sprach- / Literaturwissenschaft ► Sprachwissenschaft |
| Mathematik / Informatik ► Informatik ► Grafik / Design | |
| Informatik ► Software Entwicklung ► User Interfaces (HCI) | |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| Mathematik / Informatik ► Informatik ► Web / Internet | |
| Technik ► Elektrotechnik / Energietechnik | |
| Schlagworte | Computational Linguistics • Human-Computer interaction • Human-Computer Interaction (HCI) • Recognition • Speech Recognition • speech signal processing • Spoken Dialogue Systems • User Modeling |
| ISBN-10 | 90-481-3129-4 / 9048131294 |
| ISBN-13 | 978-90-481-3129-7 / 9789048131297 |
| Haben Sie eine Frage zum Produkt? |
PDF (Wasserzeichen)Größe: 5,5 MB
DRM: Digitales Wasserzeichen
Dieses eBook enthält ein digitales Wasserzeichen und ist damit für Sie personalisiert. Bei einer missbräuchlichen Weitergabe des eBooks an Dritte ist eine Rückverfolgung an die Quelle möglich.
Dateiformat: PDF (Portable Document Format)
Mit einem festen Seitenlayout eignet sich die PDF besonders für Fachbücher mit Spalten, Tabellen und Abbildungen. Eine PDF kann auf fast allen Geräten angezeigt werden, ist aber für kleine Displays (Smartphone, eReader) nur eingeschränkt geeignet.
Systemvoraussetzungen:
PC/Mac: Mit einem PC oder Mac können Sie dieses eBook lesen. Sie benötigen dafür einen PDF-Viewer - z.B. den Adobe Reader oder Adobe Digital Editions.
eReader: Dieses eBook kann mit (fast) allen eBook-Readern gelesen werden. Mit dem amazon-Kindle ist es aber nicht kompatibel.
Smartphone/Tablet: Egal ob Apple oder Android, dieses eBook können Sie lesen. Sie benötigen dafür einen PDF-Viewer - z.B. die kostenlose Adobe Digital Editions-App.
Buying eBooks from abroad
For tax law reasons we can sell eBooks just within Germany and Switzerland. Regrettably we cannot fulfill eBook-orders from other countries.
aus dem Bereich
