Wong Ka Ho. / Thesis submitted in: October 2005. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references (leaves 163-170). / Abstracts in English and Chinese. / Abstract --- p.2 / Acknowledgements --- p.5 / Chapter 1 --- Introduction --- p.10 / Chapter 1.1 --- Multi-modal and Multi-media --- p.10 / Chapter 1.2 --- Overview --- p.11 / Chapter 1.3 --- Thesis Goal --- p.13 / Chapter 1.4 --- Thesis Outline --- p.15 / Chapter 2 --- Background --- p.16 / Chapter 2.1 --- Multi-modal Fission --- p.17 / Chapter 2.2 --- Multi-modal Data collection --- p.21 / Chapter 2.2.1 --- Collection Time --- p.21 / Chapter 2.2.2 --- Annotation and Tools --- p.21 / Chapter 2.2.3 --- Knowledge of Multi-modal Using --- p.21 / Chapter 2.3 --- Text-to-audiovisual Speech System --- p.22 / Chapter 2.3.1 --- Different. Approaches to Generate a Talking Heading --- p.23 / Chapter 2.3.2 --- Sub-tasks in Animating a Talking Head --- p.25 / Chapter 2.4 --- Modality Selection --- p.27 / Chapter 2.4.1 --- Rules-based approach --- p.27 / Chapter 2.4.2 --- Plan-based approach --- p.28 / Chapter 2.4.3 --- Feature-based approach --- p.29 / Chapter 2.4.4 --- Corpus-based approach --- p.30 / Chapter 2.5 --- Summary --- p.30 / Chapter 3 --- Information Domain --- p.31 / Chapter 3.1 --- Multi-media Information --- p.31 / Chapter 3.2 --- "Task Goals, Dialog Acts, Concepts and Information Type" --- p.32 / Chapter 3.2.1 --- Task Goals and Dialog Acts --- p.32 / Chapter 3.2.2 --- Concepts and Information Type --- p.36 / Chapter 3.3 --- User's Task and Scenario --- p.37 / Chapter 3.4 --- Chapter Summary --- p.38 / Chapter 4 --- Multi-modal Response Data Collection --- p.41 / Chapter 4.1 --- Data Collection Setup --- p.42 / Chapter 4.1.1 --- Multi-modal Input Setup --- p.43 / Chapter 4.1.2 --- Multi-modal Output Setup --- p.43 / Chapter 4.2 --- Procedure --- p.45 / Chapter 4.2.1 --- Precaution --- p.45 / Chapter 4.2.2 --- Recording --- p.50 / Chapter 4.2.3 --- Data Size and Type --- p.50 / Chapter 4.3 --- Annotation --- p.52 / Chapter 4.3.1 --- Extensible Multi-Modal Markup Language --- p.52 / Chapter 4.3.2 --- "Mobile, Multi-biometric and Multi-modal Annotation" --- p.53 / Chapter 4.4 --- Problems in the Wizard-of-Oz Setup --- p.56 / Chapter 4.4.1 --- Lack of Knowledge --- p.57 / Chapter 4.4.2 --- Time Deficiency --- p.57 / Chapter 4.4.3 --- Information Availability --- p.58 / Chapter 4.4.4 --- Operation Delay --- p.59 / Chapter 4.4.5 --- Lack of Modalities --- p.59 / Chapter 4.5 --- Data Optimization --- p.61 / Chapter 4.5.1 --- Precaution --- p.61 / Chapter 4.5.2 --- Procedures --- p.61 / Chapter 4.5.3 --- Data Size in Expert Design Responses --- p.63 / Chapter 4.6 --- Analysis and Discussion --- p.65 / Chapter 4.6.1 --- Multi-modal Usage --- p.67 / Chapter 4.6.2 --- Modality Combination --- p.67 / Chapter 4.6.3 --- Deictic term --- p.68 / Chapter 4.6.4 --- Task Goal and Dialog Acts --- p.71 / Chapter 4.6.5 --- Information Type --- p.72 / Chapter 4.7 --- Chapter Summary --- p.74 / Chapter 5 --- Text-to-Audiovisual Speech System --- p.76 / Chapter 5.1 --- Phonemes and Visemes --- p.77 / Chapter 5.2 --- Three-dimensional Facial Animation --- p.82 / Chapter 5.2.1 --- Three-dimensional (3D) Face Model --- p.82 / Chapter 5.2.2 --- The Blending Process for Animation --- p.84 / Chapter 5.2.3 --- Connectivity between Visemes --- p.85 / Chapter 5.3 --- User Perception Experiments --- p.87 / Chapter 5.4 --- Applications and Extension --- p.89 / Chapter 5.4.1 --- Multilingual Extension and Potential Applications --- p.89 / Chapter 5.5 --- Talking Head in Multi-modal Dialogue System --- p.90 / Chapter 5.5.1 --- Prosody --- p.93 / Chapter 5.5.2 --- Body Gesture --- p.94 / Chapter 5.6 --- Chapter Summary --- p.94 / Chapter 6 --- Modality Selection and Implementation --- p.98 / Chapter 6.1 --- Multi-modal Response Examples --- p.98 / Chapter 6.1.1 --- Single Concept-value Example --- p.99 / Chapter 6.1.2 --- Two Concept-values with Different Information Types --- p.102 / Chapter 6.1.3 --- Multiple Concept-values with Same Information Types Example --- p.103 / Chapter 6.2 --- Heuristic Rules for Modality Selection --- p.105 / Chapter 6.2.1 --- General Principles --- p.106 / Chapter 6.2.2 --- Heuristic rules --- p.107 / Chapter 6.2.3 --- Temporal Coordination for Synchronization --- p.109 / Chapter 6.2.4 --- Physical Layout --- p.110 / Chapter 6.2.5 --- Deictic Term --- p.111 / Chapter 6.2.6 --- Example --- p.111 / Chapter 6.3 --- Spoken Content Generation --- p.113 / Chapter 6.4 --- Chapter Summary --- p.115 / Chapter 7 --- Conclusions and Future Work --- p.117 / Chapter 7.1 --- Summary --- p.117 / Chapter 7.2 --- Contributions --- p.118 / Chapter 7.3 --- Future work --- p.119 / Chapter A --- XML Schema for M3 Markup Language --- p.123 / Chapter B --- M3ML Examples --- p.128 / Chapter C --- Domain-Specific Task Goals in the Hong Kong Tourism Do- main --- p.131 / Chapter D --- Dialog Acts for User Request in the Hong Kong Tourism Do- main --- p.133 / Chapter E --- Dialog Acts for System Response in the Hong Kong Tourism Domain --- p.137 / Chapter F --- Information Type and Concepts --- p.141 / Chapter G --- Concepts --- p.143 / Bibliography --- p.149
| Identifer | oai:union.ndltd.org:cuhk.edu.hk/oai:cuhk-dr:cuhk_325519 |
| Date | January 2006 |
| Contributors | Wong, Ka Ho., Chinese University of Hong Kong Graduate School. Division of Systems Engineering and Engineering Management. |
| Source Sets | The Chinese University of Hong Kong |
| Language | English, Chinese |
| Detected Language | English |
| Type | Text, bibliography |
| Format | print, 170 leaves : ill. (some col.) ; 30 cm. |
| Coverage | China, Hong Kong |
| Rights | Use of this resource is governed by the terms and conditions of the Creative Commons “Attribution-NonCommercial-NoDerivatives 4.0 International” License (http://creativecommons.org/licenses/by-nc-nd/4.0/) |
Page generated in 0.006 seconds