Learn More
In this paper, we propose a robust speaker feature extraction method using kernel multimodal Fisher discriminant analysis (kernel MFDA). Kernel MFDA has been designed to have the characteristics both of kernel principal component analysis (kernel PCA) and kernel Fisher discriminant analysis (kernel FDA). Therefore, the feature vectors extracted by kernel(More)
BACKGROUND The success of allogeneic bone marrow transplantation(allo-BMT) is affected by underlying disease relapse. Although mixed chimerism(MC) is not necessarily a poor prognostic factor, several groups have suggested that MC is associated with an increased risk of disease relapse. There is evidence that patients with MC benefit from additional(More)
We propose a robust speaker identification system in noisy environments using greedy kernel principal component analysis. We expect that kernel PCA can project important information to some axes and the noise to some other axes in the arbitrary high dimensional space resulting in denoising of the input features. However, it is not easy to use kernel PCA for(More)
In this paper, we propose a classifier ensemble of various channel compensation and feature enhancement methods for robust speaker identification on various environments. The proposed ensemble system is constructed with 15 classifiers including three channel compensation methods (including CMS and variance normalization, and without compensation) and five(More)
We propose a method for histogram equalization using supplement sets to improve the performance of speaker recognition when the training and test utterances are very short. The supplement sets are derived using outputs of selection or clustering algorithms from the background speakers’ utterances. The proposed approach is used as a feature normalization(More)
This study describes the effect of surfactant concentration on the chemical mechanical polishing process of Ge1Sb6Te3 film using nanodiamond-based slurry. Aggregated diamond nanoparticles were dispersed in a slurry solution containing anionic poly(sodium 4-styrene sulfonate) using milling system. The zeta-potential, particle size and transmission electron(More)
Few studies on speaker verification have directly used a deep neural network (DNN) as a classifier. It is difficult to directly apply a DNN as a discriminative model to speaker-verification tasks because the training data for each speaker are very limited. Therefore, a b-vector has been proposed to solve the problem. However, the DNN with the b-vectors(More)
In this paper, we propose kernel multimodal Fisher discriminant analysis (kernel MFDA), a new non-linear feature transformation method, which can be applied to large-scale problems such as speaker recognition tasks. Our proposed method has characteristics of kernel Fisher discriminant analysis (kernel FDA) as well as kernel principal component analysis(More)
We propose a method to improve speaker verification performance when a test utterance is very short. In some situations with short test utterances, performance of ivector/probabilistic linear discriminant analysis systems degrades. The proposed method transforms short-utterance feature vectors to adequate vectors using a deep neural network, which(More)