Robust acoustic and semantic modeling in a telephone-based spoken dialog system [Elektronische Ressource] / Kinfe Tadesse Mengistu

Robust Acoustic and SemanticModeling in a Telephone-based SpokenDialog SystemKinfe Tadesse Mengistu (M. Sc.)Der Fakultät für Elektrotechnik und Informationstechnikder Otto-von-Guericke Universität Magdeburgzur Erlangung des akademischen GradesDoktoringenieur (Dr.-Ing.)am 27 April 2009 vorgelegte DissertationDeclarationI hereby declare that this dissertation is my autonomous work and that, to the best ofmy knowledge, it contains no material previously published or written by another person,except where due reference is made in the thesis. Any contribution made to the researchby others, with whom I have worked is explicitly acknowledged.This work has not been submitted as a dissertation to any other German or foreigninstitution and has not been previously published as a whole.April 27, 2009 MagdeburgTo my wife Yeshi and my daughter Eden for their patience, love andencouragement!AcknowledgementsWords are inadequate to express my gratitude to the Almighty God for all Hehas done to me in my life. I would like to express my heartfelt gratitude toHim in the first place.I owe a debt of gratitude to my supervisor Prof. Andreas Wendemuth for crit-ically reviewing this manuscript and enriching it with his constructive criti-cisms. He has been much more than just a supervisor. Without him, neitherthe start nor the completion of this research work would have been possible.Many thanks are due to him!