Authors IndexSessionsTechnical programAttendees

	Oral Session I:  ASR Robustness (Feature Extraction,Acoustic Modeling and Adaptation)
	Session Chair: Alex Potamianos (Bell Labs - Lucent Technologies, USA) Invited speakers Vasilios Digalakis  Mark Gales Adaptive Training for Robust ASR

Poster Session I:   ASR Robustness (Feature Extraction,Acoustic Modeling and Adaptation)

Histogram Based Normalization in the Acoustic Feature Space Sirko Molau, Hermann Ney, Michael Pitz   An Improved Union Model for Continuous Speech Recognition with Partial Duration Corruption Ming Ji   A Comparative Study of Model-Based Adaptation Techniques for a Compact Speech Recognizer Frank Thiele, Rolf Bippus   Gaussian Mixture Models of Phonetic Boundaries For Speech Recognition Mohamed Kamal Omar, Mark Hasegawa-Johnson, Stephen Levinson   Multiple Time Resolutions for Derivatives of Mel-frequency Cepstral Coefficients Georg Stemmer, Christian Hacker, Elmar Nöth, Heinrich Niemann   Continuous Multi-Band Speech Recognition using Bayesian Networks Khalid Daoudi, Dominique Fohr, Christophe Antoine   Trend Tying in the Segmental-feature HMM Young-Sun Yun   Improved MFCC Feature Extraction by PCA-Optimized Filter-bank for Speech Recognition Shang-Ming Lee, Shi-Hau Fang, Jeih-weih Hung, Lin-Shan Lee   Improved Pronunciation Modelling by Inverse Word Frequency and Pronunciation Entropy Ming-yi Tsai, Fu-chiang Chou, Lin-shan Lee   Robust Speaker Clustering in Eigenspace Robert Faltlhauser, Guenther Ruske   Speaker-Trained Recognition using Allophonic Enrollment Models Vincent Vanhoucke, Michael Hochberg, Christopher Leggetter   Speech Recognition using Advanced HMM2 Features Katrin Weber, Samy Bengio , Herve Bourlard   WITHDRAWN: Unconstrained Multiple Prototype HMM Design for Speech Recognition Liang Gu, Kenneth Rose   Construction of Model-Space Constraints Patrick Nguyen, Luca Rigazio, Christian Wellekens, Jean-Claude Junqua   Eliminating Inter-Speaker Variability Prior to Discriminant Transforms George Saon, Mukund Padmanabhan   Acoustic Factorisation Mark Gales   Recursive Noise Estimation Using Iterative Stochastic Approximation for Stereo-Based Robust Speech Recognition Li Deng, Jasha Droppo, Alex Acero

Back to session index