1-4hit |
Yousuke NARUSE Jun-ichi TAKADA
We introduce a MIMO channel estimation method that exploits the channel's spatiotemporal correlation without the aid of a priori channel statistical information. A simplified Gauss-Markov model that has fewer parameters to be estimated is presented for the Kalman filter. In order to obtain statistical parameters on the time evolution of the channel, considering that the time evolution is a latent statistical variable, the expectation-maximization (EM) algorithm is applied for accurate estimation. Numerical simulations reveal that the proposed method is able to enhance estimation capability by exploiting spatiotemporal correlations, and the method works well even if the forgetting factor is small.
Kernel logistic regression (KLR) is a powerful and flexible classification algorithm, which possesses an ability to provide the confidence of class prediction. However, its training--typically carried out by (quasi-)Newton methods--is rather time-consuming. In this paper, we propose an alternative probabilistic classification algorithm called Least-Squares Probabilistic Classifier (LSPC). KLR models the class-posterior probability by the log-linear combination of kernel functions and its parameters are learned by (regularized) maximum likelihood. In contrast, LSPC employs the linear combination of kernel functions and its parameters are learned by regularized least-squares fitting of the true class-posterior probability. Thanks to this linear regularized least-squares formulation, the solution of LSPC can be computed analytically just by solving a regularized system of linear equations in a class-wise manner. Thus LSPC is computationally very efficient and numerically stable. Through experiments, we show that the computation time of LSPC is faster than that of KLR by two orders of magnitude, with comparable classification accuracy.
Hongbin SUO Ming LI Ping LU Yonghong YAN
Robust automatic language identification (LID) is the task of identifying the language from a short utterance spoken by an unknown speaker. The mainstream approaches include parallel phone recognition language modeling (PPRLM), support vector machine (SVM) and the general Gaussian mixture models (GMMs). These systems map the cepstral features of spoken utterances into high level scores by classifiers. In this paper, in order to increase the dimension of the score vector and alleviate the inter-speaker variability within the same language, multiple data groups based on supervised speaker clustering are employed to generate the discriminative language characterization score vectors (DLCSV). The back-end SVM classifiers are used to model the probability distribution of each target language in the DLCSV space. Finally, the output scores of back-end classifiers are calibrated by a pair-wise posterior probability estimation (PPPE) algorithm. The proposed language identification frameworks are evaluated on 2003 NIST Language Recognition Evaluation (LRE) databases and the experiments show that the system described in this paper produces comparable results to the existing systems. Especially, the SVM framework achieves an equal error rate (EER) of 4.0% in the 30-second task and outperforms the state-of-art systems by more than 30% relative error reduction. Besides, the performances of proposed PPRLM and GMMs algorithms achieve an EER of 5.1% and 5.0% respectively.
This paper presents a view independent video-based face recognition method using posterior probability in Kernel Fisher Discriminant (KFD) space. In practical environment, the view of faces changes dynamically. Robustness to view changes is required for video-based face recognition in practical environment. Since the view changes induce large non-linear variation, kernel-based methods are appropriate. We use KFD analysis to cope with non-linear variation. To classify image sequence, the posterior probability in KFD space is used. KFD analysis assumes that the distribution of each class in high dimensional space is Gaussian. This makes the computation of posterior probability in KFD space easy. The combination of KFD space and posterior probability of image sequence is the main contribution of the proposed method. The performance is evaluated by using two face databases. Effectiveness of the proposed method is shown by the comparison with the other feature spaces and classification methods.