Speaker: Roger Wend-Huu Hsiao
Title: Kernel Eigenspace-based MLLR Adaptation
Abstract:
Eigenspace-based adaptation methods have been shown effective 
for fast speaker adaptation when the amount of adaptation data 
is small (for example, less than 10s). Recently, the application 
of kernel methods to improve the performance of these eigenspace-based 
adaptation methods was proposed. Kernel eigenspace-based MLLR 
adaptation (KEMLLR) method is one of the kernelized speaker 
adaptation methods, which tries to exploit the possible non-linearity 
in the speaker transformation supervector space. In KEMLLR, 
speaker-dependent MLLR transformation matrices are mapped to a 
kernel-induced high dimensional feature space, and kernel principal 
component analysis (KPCA) is used to derive a set of eigenmatrices in 
the feature space. A new speaker is then represented by a linear 
combination of the leading eigenmatrices. 
In this talk, KEMLLR adaptation will be compared with other adaptation 
methods including MAP, MLLR, eigenvoice (EV), and embedded kernel 
eigenvoice (eKEV) on the Resource Management and Wall Street Journal 
tasks using 5s or 10s of adaptation speech.

Speaker bio:
Roger Wend-Huu Hsiao received the B.Eng. degree and M.Phil. degree in 
Computer Science in 2002 and 2004, both from the Hong Kong University of 
Science and Technology (HKUST). From 2004 to 2005, he was a research 
assistant in the Human Language Technology Center of HKUST. Since August 
2005 he is a graduate student at the Language Technologies Institute, 
School of Computer Science, Carnegie Mellon University, Pittsburgh, 
Pennsylvania. His research interests include speech recognition, speaker 
adaptation and kernel methods.