James Tin-Yau Kwok

Embedded kernel eigenvoice speaker adaptation and its implication to reference speaker weighting (2006)

Mak, Brian Kan-Wing, Hsiao, Roger, Ho, Simon, Kwok, James Tin-Yau

Recently, we proposed an improvement to theconventional eigenvoice (EV) speaker adaptation using kernel methods. In our novel kernel eigenvoice (KEV) speaker adaptation [1], speaker supervectors are...

Embedded kernel eigenvoice speaker adaptation and its implication to reference speaker weighting (2006)

Mak, Brian Kan-Wing, Hsiao, Roger, Ho, Simon, Kwok, James Tin-Yau

Recently, we proposed an improvement to theconventional eigenvoice (EV) speaker adaptation using kernel methods. In our novel kernel eigenvoice (KEV) speaker adaptation [1], speaker supervectors are...

Model-based transductive learning of the kernel matrix (2006)

Zhang, Zhihua, Kwok, James Tin-Yau, Yeung, Dit-Yan

This paper addresses the problem of transductive learning of the kernel matrix from a probabilistic perspective. We define the kernel matrix as a Wishart process prior and construct a hierarchical...

Fusing images with different focuses using support vector machines (2004)

Li, Shutao, Kwok, James Tin-Yau, Tsang, Ivor W., Wang, Yaonan

Many vision-related processing tasks, such as edge detection, image segmentation and stereo matching, can be performed more easily when all objects in the scene are in good focus. However, in...

Surrogate maximization/minimization algorithms for AdaBoost and the logistic regression model (2004)

Zhang, Zhihua, Kwok, James Tin-Yau, Yeung, Dit-Yan

Surrogate maximization (or minimization) (SM) algorithms are a family of algorithms that can be regarded as a generalization of expectation-maximization (EM) algorithms. There are three major...

Bayesian inference on principal component analysis using reversible jump Markov chain Monte Carlo (2004)

Zhang, Zhihua, Chan, Kap Luk, Kwok, James Tin-Yau, Yeung, Dit-Yan

Based on the probabilistic reformulation of principal component analysis (PCA), we consider the problem of determining the number of principal components as a model selection problem. We present a...

Bayesian inference for transductive learning of kernel matrix using the Tanner-Wong data augmentation algorithm (2004)

Zhang, Zhihua, Yeung, Dit-Yan, Kwok, James Tin-Yau

In kernel methods, an interesting recent development seeks to learn a good kernel from empirical data automatically. In this paper, by regarding the transductive learning of the kernel matrix as a...