Adaptation of Acoustic and Language Model for Improving Arabic Automatic Speech Recognition

Abstract

First and foremost, I thank Almighty Allah for giving me the inspiration, patience, determination and strength to complete this work successfully I would like to express my sincere thanks and appreciation to my supervisor Prof.Alaa El-Halees (Deputy Dean of Information Technology Faculty) for his excellent comments on my research that considerably improved this thesis. Further, my thanks also go to Dr. Basem Ahmed for his help, discussions, and experimental setup for CMU Sphinx-III during my work on this research. Without their help, my work on ASR system will be much more difficult to accomplish. Also I would like to thank King Fahd University of Petroleum and Minerals (KFUPM), and Prof. Moustafa Elshafei for providing the broadcast news corpus to work this research. I am greatly indebted to my mother and my father, who are devotedly have spent their lives to motivate their children to pursue their higher education. I thank also my mother for remembering me in her prayers day and night during my research. In addition, I would like to thank dear my brothers. Also I would like to thank my wife Hanan for her constant love and encouragement and shouldering an extraordinary responsibility for dealing with two kids (Karam and Abd Al-Rahman) during my work on the master degree. I thank my wife and kids for their patience. Last but not least, for everyone who has helped and supported me to reach this stage; I would say Thank You.