The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Recurrent neural network language models have solved the problems of data sparseness and dimensionality disaster which exist in traditional N-gram models. RNNLMs have recently demonstrated state-of-the-art performance in speech recognition, machine translation and other tasks. In this paper, we improve the model performance by providing contextual word vectors in association with RNNLMs. This method...
The performance analyses of Z-type models using PSAF (i.e., power-sigmoid activation functions) for solving the Zhang problems are investigated in this paper. Excellent robustness is demonstrated when using PSAF for very large perturbation errors. Compared with LAF (i.e., linear activation functions), Z-type models using PSAF have better performance on solving not only scalar-valued problems but also...
The d-q transformation is widely used in the three-phase system analysis, targeting for symmetrical and balanced systems where the time-varying line-frequency sinusoidal terms of the system state variables can be fully canceled out. With the introduction of the distributed generations, more and more unbalanced infrastructures can be connected to the grid, creating unbalanced systems. It will be desirable...
Presents an optimization algorithm about cubic NURBS based on internal k-order- derivative constraints, and according to reset those control points, node vectors and weights, we can extend the NURBS curves to one target point or more target points. And we also prove those methods' effectiveness through some specific examples.
A new soft relevance technique for scene categorization is proposed in this paper. A popular approach for scene categorization is the Bag-of-Words (BoW) framework, where a histogram is calculated for each image as the image signature. However, in most of the existing BoW based image classification methods, all the image signatures are regarded equally, so the outlier images may be harmful to the classification...
By combining Fractional Spectral Subtraction (FSS) with Perceptual Linear Predictive (PLP), a hybrid method of noise robustness speech recognition isinvestigated in this paper. This method uses FSS for noisy speech to reduce noise components in the fractional Fourier domain. According to the results ofcomputing Itakura distance and Mean Square Error (MSE), an approximate optimal fractional order is...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.