Multimodal signal processing: theory and applications for human-computer interaction
1st ed.. - Amsterdam, Boston: Academic, 2010
Online
Bibliografie, Monographie, Elektronische Ressource
- 1 online resource (343 p.)
Online verfügbar:
Ermittle Ausleihstatus...
Multimodal signal processing is a 'hot' new area with applications in security (user identification) and medical health. Often these applications will be sensor networks, an area that is getting massive funding. Multi-modal refers to the different types of signals received from different source types: vision, speech, touch, smell and text. Processing these signals requires very different signal processing methods and techniques. This book provides the definitive reference on multimodal signal processing by the world's experts, giving state-of-the-art methods in multimodal signal and im
Front Cover; Title Page; Copyright Page; Table of Contents; Preface; Chapter 1. Introduction; Part I: Signal Processing, Modelling and Related Mathematical Tools; Chapter 2. Statistical Machine Learning for HCI; 2.1 Introduction; 2.2 Introduction to Statistical Learning; 2.2.1 Types of Problem; 2.2.2 Function Space; 2.2.3 Loss Functions; 2.2.4 Expected Risk and Empirical Risk; 2.2.5 Statistical Learning Theory; 2.3 Support Vector Machines for Binary Classification; 2.4 Hidden Markov Models for Speech Recognition; 2.4.1 Speech Recognition; 2.4.2 Markovian Processes; 2.4.3 Hidden Markov Models
2.4.4 Inference and Learning with HMMs2.4.5 HMMs for Speech Recognition; 2.5 Conclusion; References; Chapter 3. Speech Processing; 3.1 Introduction; 3.2 Speech Recognition; 3.2.1 Feature Extraction; 3.2.2 Acoustic Modelling; 3.2.3 Language Modelling; 3.2.4 Decoding; 3.2.5 Multiple Sensors; 3.2.6 Confidence Measures; 3.2.7 Robustness; 3.3 Speaker Recognition; 3.3.1 Overview; 3.3.2 Robustness; 3.4 Text-to-Speech Synthesis; 3.4.1 Natural Language Processing for Speech Synthesis; 3.4.2 Concatenative Synthesis with a Fixed Inventory; 3.4.3 Unit Selection-Based Synthesis
3.4.4 Statistical Parametric Synthesis3.5 Conclusions; References; Chapter 4. Natural Language and Dialogue Processing; 4.1 Introduction; 4.2 Natural Language Understanding; 4.2.1 Syntactic Parsing; 4.2.2 Semantic Parsing; 4.2.3 Contextual Interpretation; 4.3 Natural Language Generation; 4.3.1 Document Planning; 4.3.2 Microplanning; 4.3.3 Surface Realisation; 4.4 Dialogue Processing; 4.4.1 Discourse Modelling; 4.4.2 Dialogue Management; 4.4.3 Degrees of Initiative; 4.4.4 Evaluation; 4.5 Conclusion; References; Chapter 5. Image and Video Processing Tools for HCI; 5.1 Introduction
5.2 Face Analysis5.2.1 Face Detection; 5.2.2 Face Tracking; 5.2.3 Facial Feature Detection and Tracking; 5.2.4 Gaze Analysis; 5.2.5 Face Recognition; 5.2.6 Facial Expression Recognition; 5.3 Hand-Gesture Analysis; 5.4 Head Orientation Analysis and FoA Estimation; 5.4.1 Head Orientation Analysis; 5.4.2 Focus of Attention Estimation; 5.5 Body Gesture Analysis; 5.6 Conclusions; References; Chapter 6. Processing of Handwriting and Sketching Dynamics; 6.1 Introduction; 6.2 History of Handwriting Modality and the Acquisition of Online Handwriting Signals
6.3 Basics in Acquisition, Examples for Sensors6.4 Analysis of Online Handwriting and Sketching Signals; 6.5 Overview of Recognition Goals in HCI; 6.6 Sketch Recognition for User Interface Design; 6.7 Similarity Search in Digital Ink; 6.8 Summary and Perspectives for Handwriting and Sketching in HCI; References; Part II: Multimodal Signal Processing and Modelling; Chapter 7. Basic Concepts of Multimodal Analysis; 7.1 Defining Multimodality; 7.2 Advantages of Multimodal Analysis; 7.3 Conclusion; References; Chapter 8. Multimodal Information Fusion; 8.1 Introduction; 8.2 Levels of Fusion
Titel: |
Multimodal signal processing: theory and applications for human-computer interaction
|
---|---|
Verantwortlichkeitsangabe: | edited by Jean-Philippe Thiran, Ferran Marqués, Hervé Bourlard |
Autor/in / Beteiligte Person: | Thiran, Jean-Philippe [author.] ; Bourlard, Hervé (1956-) ; Marques, Ferran ; Thiran, Jean-Philippe |
Lokaler Link: | |
Verknüpfte Werke: | |
Ausgabe: | 1st ed. |
Veröffentlichung: | Amsterdam, Boston: Academic, 2010 |
Medientyp: | Bibliografie, Monographie |
Datenträgertyp: | Elektronische Ressource |
Umfang: | 1 online resource (343 p.) |
ISBN: | 1-282-48170-3; 9786612481703; 0-08-088869-0 |
Schlagwort: |
|
Sonstiges: |
|