Search

An algorithm for real-time speech stretching is presented. It was designed to modify input signal dependently on its content and on its relation with the historical input data. The proposed algorithm is a combination of speech signal analysis algorithms, i.e. voice, vowels/consonants, stuttering detection and SOLA (Synchronous-Overlap-and-Add) based speech stretching algorithm. This approach enables stretching input speech signal in real-time with high quality and provides "global" synchronization of the input and output signals. Finally, the effectiveness of the engineered algorithms as well as the quality of the processed speech are discussed. [ABSTRACT FROM AUTHOR]

In this paper, we present a handwritten character recognition (HCR) system that aims to recognize first-order logic handwritten formulas and create editable text files of the recognized formulas. Dense feedforward neural networks (NNs) are utilized, and their performance is examined under various training conditions and methods. More specifically, after three training algorithms (backpropagation, resilient propagation and stochastic gradient descent) had been tested, we created and trained an NN with the stochastic gradient descent algorithm, optimized by the Adam update rule, which was proved to be the best, using a trainset of 16,750 handwritten image samples of 28 × 28 each and a testset of 7947 samples. The final accuracy achieved is 90.13%. The general methodology followed consists of two stages: the image processing and the NN design and training. Finally, an application has been created that implements the methodology and automatically recognizes handwritten logic formulas. An interesting feature of the application is that it allows for creating new, user-oriented training sets and parameter settings, and thus new NN models. [ABSTRACT FROM AUTHOR]

Describes a nonlinear tomographic reconstruction algorithm developed for inversion of traveltime measurements that rely on perturbations of the straight line ray wave propagation model. Definition of the nonlinear data-generating models for traveltime tomography; Volterra expansions considered; Examination of the nonlinear tomographic inversion of traveltime data; Computer simulation of the nonlinear inversion algorithms.

We revisit geophysical diffraction tomography (GDT) and cast it into a stochastic framework, in which the geophysical formation to be imaged is modeled as a realization of a two-dimensional stationary random process. it is shown that the optimum reconstruction algorithm, in both the cases of offset vertical seismic profiling and well-to-well probing, attains a modified filtered backpropagation form. [ABSTRACT FROM AUTHOR]