A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that often attributable speaker differences. Speaker adaptation techniques play a vital role mismatch. Model-based approaches require sufficient amounts of target ensure robustness. When amount level limited, prone overfitting poor generalization. To address issue, this paper proposes full B...

Deep neural network is a state-of-art method in modern science and technology. Much statistical literature have been devoted to understanding its performance nonparametric estimation, whereas the results are suboptimal due redundant logarithmic sacrifice. In this paper, we show that such log-factors not necessary. We derive upper bounds for L 2 minimax risk estimation. Sufficient conditions on ...

Modern geosteering is heavily dependent on real-time interpretation of deep electromagnetic (EM) measurements. We present a methodology to construct neural network (DNN) model trained reproduce full set extra-deep EM logs consisting 22 measurements per logging position. The in 1D layered environment up seven layers with different resistivity values. A commercial simulator provided by tool vendo...

We propose a scalable Gaussian process model for regression by applying a deep neural network as the feature-mapping function. We first pre-train the deep neural network with a stacked denoising auto-encoder in an unsupervised way. Then, we perform a Bayesian linear regression on the top layer of the pre-trained deep network. The resulting model, Deep-Neural-Network-based Gaussian Process (DNN-...