ISBN:
9789048131297
,
9789048131280
Language:
English
Pages:
Online-Ressource (X, 276p, digital)
Series Statement:
SpringerLink
Series Statement:
Bücher
Parallel Title:
Druckausg. u.d.T. Pittermann, Johannes, 1977 - Handling emotions in human-computer dialogues
DDC:
006.454
Keywords:
Information systems
;
Multimedia systems
;
Computer science
;
Computational linguistics
;
Linguistics
;
Computational linguistics
;
Computer science
;
Information systems
;
Linguistics
;
Multimedia systems
;
Automatic speech recognition
;
Human-computer interaction
;
Emotions
;
Computer simulation
;
Mensch-Maschine-Kommunikation
;
Automatische Spracherkennung
;
Gefühl
;
Computersimulation
;
Mensch-Maschine-Kommunikation
;
Automatische Spracherkennung
;
Gefühl
;
Computersimulation
Abstract:
As computer technology develops, spoken dialogue is becoming ever-more important when interacting with a wide variety of technological devices, including Personal Digital Assistants, tablet PCs, and mobile phones. Using speech leads to more natural and user-friendly interfaces. More specifically, the authors of this volume contend that the experience of talking to our computerized gadgets may be greatly improved by dynamically adapting the system's dialogue interaction style to the user's profile and emotional status. 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.
Description / Table of Contents:
Handling Emotions in Human-Computer Dialogues; Preface; Contents; 1 Introduction; 1.1 Spoken Language Dialogue Systems; 1.1.1 Automatic Speech Recognition; 1.1.2 Natural Language Understanding; 1.1.3 Dialogue Management; 1.1.4 Text Generation; 1.1.5 Text-to-Speech; 1.2 Enhancing a Spoken Language Dialogue System; 1.3 Challenges in Dialogue Management Development; 1.4 Issues in User Modeling; 1.5 Evaluation of Dialogue Systems; 1.6 Summary of Contributions; 2 Human Emotions; 2.1 Definition of Emotion; 2.2 Theories of Emotion and Categorization; 2.3 Emotional Labeling
Description / Table of Contents:
2.4 Emotional Speech Databases/Corpora2.5 Discussion; 3 Adaptive Human-Computer Dialogue; 3.1 Background and Related Research; 3.1.1 Adaptive Dialogue Management; 3.1.2 Stochastic Approaches to Dialogue Modeling; 3.1.3 Emotions in Dialogue Systems; 3.2 User-State and Situation Management; 3.3 Dialogue Strategies and Control Parameters; 3.4 Integrating Speech Recognizer Confidence Measures into Adaptive Dialogue Management; 3.5 Integrating Emotions into Adaptive Dialogue Management; 3.6 A Semi-Stochastic Dialogue Model; 3.7 A Semi-Stochastic Emotional Model
Description / Table of Contents:
3.8 A Semi-Stochastic Combined Emotional Dialogue Model3.9 Extending the Semi-Stochastic Combined Emotional Dialogue Model; 3.10 Discussion; 4 Hybrid Approach to Speech-Emotion Recognition; 4.1 Signal Processing; 4.1.1 Preprocessing; 4.1.2 Linear Prediction; 4.1.3 Mel-Frequency Cepstral Coefficients; 4.1.4 Prosodic and Acoustic Features; 4.2 Classifiers for Emotion Recognition; 4.2.1 Hidden Markov Models; 4.2.2 Artificial Neural Networks; 4.3 Existing Approaches to Emotion Recognition; 4.4 HMM-Based Speech Recognition; 4.5 HMM-Based Emotion Recognition
Description / Table of Contents:
4.6 Combined Speech and Emotion Recognition4.7 Emotion Recognition by Linguistic Analysis; 4.8 Discussion; 5 Implementation; 5.1 Emotion Recognizer Optimizations; 5.1.1 Plain Emotion Recognition; 5.1.2 Speech-Emotion Recognition; 5.2 Using Multiple (Speech-)Emotion Recognizers; 5.2.1 ROVER for Emotion Recognition; 5.2.2 ROVER for Speech-Emotion Recognition; 5.3 Implementation of Our Dialogue Manager; 5.4 Discussion; 6 Evaluation; 6.1 Description of Dialogue System Evaluation Paradigms; 6.2 Speech Data Used for the Emotion Recognizer Evaluation; 6.3 Performance of Our Emotion Recognizer
Description / Table of Contents:
6.3.1 Plain Emotion Recognition6.3.2 Speech-Emotion Recognition; 6.3.3 Combining Multiple Speech-Emotion Recognizers; 6.3.4 Emotion Recognition by Linguistic Analysis; 6.4 Evaluation of Our Dialogue Manager; 6.5 Discussion; 7 Conclusion and Future Directions; A Emotional Speech Databases; B Used Abbreviations; References; Index;
Note:
Includes bibliographical references and index
DOI:
10.1007/978-90-481-3129-7
URL:
Volltext
(lizenzpflichtig)
Permalink