Robust Modeling of Dialog Acts Using Language and Speech

I am submitting herewith a thesis written by Mohammad Shahed Sorower entitled " Robust Modeling of Dialog Acts using Language and Speech ". I have examined the final copy of this thesis for form and content and recommend that it be accepted in partial fulfillment of the requirements for the degree of Master of Science with a major in Electrical and Computer Engineering. In presenting this thesis as a partial fulfillment of the requirements for the master's degree at The Universiy of Memphis, I agree that the library shall make it available to borrowers under the rules of the library. Brief quotations from this thesis are allowable without special permission, provided that accurate acknowledgement of the source is made. Permission for extensive quotation from reproduction of this thesis may be granted by major professor, or in his absence, by the Head of the interlibrary services when in opinion of either, the proposed use of the material is for scholarly purposes. Any copying or use of the material in this thesis for financial gain shall not be allowed without my written permission. ii DEDICATION To all the teachers I had in my life ……… My mother, who had been my first teacher and a guide throughout my life. Also to all the teachers I had in my life, especially those I owe my achievements to beside my knowledge and enlightenment. iii ACKNOWLEDGEMENTS First, I would like to thank my supervisor Dr. Mohammed Yeasin for his support throughout this thesis, for all his patience and guidance. I would also like to thank Dr. for proving valuable guidance and suggestions for this work. I am also grateful to all my colleagues from Computer Vision, Pattern and Image Analysis (CVPIA) Lab for their helps with experiments, coding and sincere encouragements; special thanks to Mr. Gahangir Hossain for sincerely scrutinizing the complete thesis. I sincerely thank Human Communication Research Center (HCRC) at University of Edinburgh for sharing HCRC Map Task data for our use in this thesis. I also thank Dr. Max Louwerse for taking the procedure to get this data from University of Edinburgh and let us have access to that. I am also obliged to Herff College of Engineering, The University of Memphis, for offering me Herff Graduate Fellowship that was a great honor and encouragement for me. I would like to express my personal gratitude and appreciation for Mafruhatul Jannat, who always …