Quantile based histogram equalization for noise robust speech recognition [Elektronische Ressource] / von Florian Erich Hilger

Quantile Based Histogram Equalizationfor Noise Robust Speech RecognitionVon der Fakult at fur Mathematik, Informatikund Naturwissenschaftender Rheinisch-Westf alischen Technischen Hochschule Aachengenehmigte Dissertation zur Erlangung des akademischenGrades eines Doktors der NaturwissenschaftenvonDiplom{Physiker Florian Erich HilgerausBonn { Bad GodesbergBerichter: Univ.-Prof. Dr.-Ing. Hermann NeyHon.-Prof. Dr. phil. nat. Harald H ogeTag der mundlic hen Prufung: 6. Dezember 2004Diese Dissertation ist auf den Internetseiten der Hochschulbibliothek online verfugbar.AcknowledgementsI would like to thank my supervisor Prof. Dr.{Ing. Hermann Ney for his constant support,his valuable advice, and giving me the opportunity to realize this work at the Lehrstuhlfur Informatik VI in Aachen.Prof. Dr. phil. nat. Harald H oge from Siemens AG Munich kindly took over the roleof the second supervisor. I would like to thank him for his interest in this work and hissuggestions.The joint work of my colleagues from the speech recognition group provided the neces-sary foundation, on which I could build my research. I would like to express my gratitudefor the contributions of Maximilian Bisani, Stephan Kanthak, Klaus Macherey, WolfgangMacherey, Sirko Molau, Michael Pitz, Ralf Schluter, Achim Sixtus, Tibor Szilassy, FrankWessel, and Andr as Zolnay.