Roger Hsiao

Also published under:Roger Wend-Huu Hsiao, R. Hsiao

Affiliation

InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA

Topic

Acoustic Model,Speech Recognition,Auxiliary Function,Continuous Recognition,Discrimination Training,Feature Space,Hidden Markov Model,Mahalanobis Distance,Maximum Mutual Information,Mean Vector,Speech Recognition Systems,Training Set,Adaptive Method,Audio Data,Automatic Speech Recognition System,Baseline System,Context Window,Cross-entropy,Decoding,Dual Problem,Dual Variables,Eigenmodes,Eigenspace,Fast Adaptation,Fast Algorithm,Feature Dimension,Feature Transformation,Gaussian Mixture Model,Gradient Ascent,High-dimensional Feature,Hourly Data,Improve Recognition Performance,Input Space,Isotropic Gaussian Kernel,Kernel Function,Kernel Methods,Kernel Principal Component Analysis,Kernel Values,Lagrange Multiplier,Language Model,Lexical Entries,Linear Transformation,Log-likelihood,ML Models,Maximum A Posteriori,Maximum Likelihood Estimation,Maximum Likelihood Linear Regression,Maximum Likelihood Model,Mel-frequency Cepstral Coefficients,Mutual Information,

Biography

Roger Wend-Hun Hsiao (S'05) received the B.Eng. and M.Phil. degrees in computer science from the Hong Kong University of Science and Technology (HKUST) in 2002 and 2004, respectively. He is currently pursuing the Ph.D. degree at the Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA.
From 2004 to 2005, he was a Research Assistant in the Human Language Technology Center, HKUST, under the guidance of Dr. B. Mak. His research interests include speech recognition, speaker adaptation, and kernel methods.