Accurate modeling of co-articulation, the contextsensitive merging of the boundaries between allophones in continuous speech, is vital for natural sounding speech synthesis. This paper describes initial research investigating the use of Bézier Curves to form models of co-articulation in human speech. A 12th order, pitch synchronous line spectral pair (LSP) [1] analysis is performed on a corpus ...

Model-based recognition and motion tracking depends upon the ability to solve for projection and model parameters that will best fit a 3-D model to matching 2-D image features. This paper extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulations, variable dimensions, or surface deformations...

To meet the requirements of the EU Water Framework Directive, models are useful to predict communities in watercourses based on the abiotic characteristics of their aquatic environment. For that purpose back-propagation artificial neural network algorithms were used to induce predictive models on a dataset of the Zwalm river basin (Flanders, Belgium). This dataset consisted of 120 samples, coll...

In this work a feed-forward NN based NAR model for forecasting time series is presented. The learning rule used to adjust the NN weights is based on the LevenbergMarquardt method. In function of the long or short term stochastic dependence of the time series, we propose an online heuristic law to set the training process and to modify the NN topology. The approach is tested over five time serie...

Unbiased and consistent estimates of structure and motion can be obtained by least squares minimization of the differential epipolar constraint. Previous work on this subject does not make use of geometrical constraints that often are present in natural and man built scenes. This paper shows how linear constraints among feature points (collinearity and coplanarity) and bilinear relations among ...

This paper presents a comparative study of different neural network models for forecasting the weather of Vancouver, British Columbia, Canada. For developing the models, we used one year’s data comprising of daily maximum and minimum temperature, and wind-speed. We used Multi-Layered Perceptron (MLP) and an Elman Recurrent Neural Network (ERNN), which were trained using the one-step-secant and ...

Artificial neural networks (ANN) is an approach to solving different tasks. In this paper we forecast U.S. stock market movements using two types of artificial neural networks: a network based on the Levenberg-Marquardt learning mechanism and a synergetic network which was described by German scientist Herman Haken. The LevenbergMarquardt ANN is widely used for forecasting financial markets, wh...

In this paper we consider the problem of recovering the drift function of a Brownian motion from its distribution of first passage times, given a fixed starting position. Our approach uses the backward Kolmogorov equation for the probability density function (pdf) of first passage times. By taking Laplace Transforms, we reduce the problem to calculating the coefficient function in a second orde...

Precise camera calibration is a core requirement of location system and augmented reality. In this paper, we propose a method to estimate camera motion parameter based on invariant point features. Typically, feature information of image has drawback, it is variable to camera viewpoint, and therefore information quantity increases after time. The LM(LevenbergMarquardt) method using nonlinear min...