Artificial Intelligence and Robotics Commons^™

A Computer-Based Articulation Training Aid For Short Words (Cata), Mukund Devarajan

Electrical & Computer Engineering Theses & Dissertations

Several improvements in the vowel articulation training aid (VATA) are described, as well as the efforts to extend the visual feedback system to operate with short words in the form of consonant, vowel and consonant (CVC). The extended version of the visual feedback system is referred to as CATA (Computer-based Articulation Training Aid); the vowel version of the aid (VATA) only operates with ten American English monopthong vowels. Improvements in VATA include the use of a neural network (NN) recognizer method to prune a large database of vowel recordings to eliminate noisy and/or mispronounced tokens. The spectral jitter problem, previously …

Automatic Speaker Identification Using Reusable And Retrainable Binary-Pair Partitioned Neural Networks, Ashutosh Mishra

Electrical & Computer Engineering Theses & Dissertations

This thesis presents an extension of the work previously done on speaker identification using Binary Pair Partitioned (BPP) neural networks. In the previous work, a separate network was used for each pair of speakers in the speaker population. Although the basic BPP approach did perform well and had a simple underlying algorithm, it had the obvious disadvantage of requiring an extremely large number of networks for speaker identification with large speaker populations. It also requires training of networks proportional to the square of the number of speakers under consideration, leading to a very large number of networks to be trained …

A Multilevel Neural Network Architecture For Digital Implementation Of A Face Recognition System Based On Eigenface Approach, Linda Rajan

Electrical & Computer Engineering Theses & Dissertations

The design and development of the digital implementation of a multilevel feed forward neural network architecture for face recognition based on statistical features representing Eigenfaces is presented in this thesis. The architecture is divided into three parts: feature extractor, classifier and identifier, The Eigenface extractor architecture is developed based on an efficient design strategy in which all the M weight values corresponding to the Eigenfaces are generated simultaneously from M images representing the Eigen vectors and the test input image. The multilayer neural network classifier is trained using error backpropagation algorithm. A novel multilevel digital architecture is developed for the …

Newton Parameter Update Algorithm For Recurrent Neural Networks Applied To Adaptive System Identification And Control, Donald Allen Gates

Electrical & Computer Engineering Theses & Dissertations

This paper shows that the combination of a second-order neural network parameter update algorithm and internal network feedback can be effectively used for adaptive, nonlinear, dynamical system identification and control. Adaptive neural identification and control algorithms are typically utilized for real-time applications where the rate of adaptation is often critical. A fast, adaptive network parameter update algorithm is presented.

Simulation results show that this algorithm is capable of quickly identifying and adapting to changes in system parameters, making it feasible to use for real-time control and fault accommodation applications.

Velocity Estimation Via A Neural Network Enhanced By Classical Detection Algorithms, Zeki Berk Hamşioğlu

Electrical & Computer Engineering Theses & Dissertations

The goal of this research is to show how to solve a velocity estimation problem using a neural network connected to an array of sensors. Motivated by biological studies involving insect vision, the neural network utilized is a member of a class of shunting neural networks. When an object moves across the face of the sensor array, the neural network's pulse response is first temporally located using classical M-ary detection techniques. Both the deterministic and stochastic cases are considered. Then the network's pulse response is post-processed via an existing velocity estimation algorithm based on a Volterra series model of the …

Text Independent Speaker Verification Using Binary-Pair Partitioned Neural Networks, Claude A. Norton Iii

Electrical & Computer Engineering Theses & Dissertations

A method is presented for the application of binary-pair partitioned neural networks to the task of speaker verification. This technique is based on a previously developed neural network classifier for speaker identification.

The main focus of this research was the development and testing of the algorithms necessary to extend the binary-pair partitioning approach from speaker identification to speaker verification. The method is based on the development of a user profile which is obtained from discriminative data provided by the binary-pair partitioned neural networks.

Experimental results are provided which demonstrate the viability of this approach, using the TIMIT speech corpus for …

Recognition Of Quadric Surfaces From Range Data: An Analytical Approach, Ivan X. D. D'Cunha

Electrical & Computer Engineering Theses & Dissertations

In this dissertation, a new technique based on analytic geometry for the recognition and description of three-dimensional quadric surfaces from range images is presented. Beginning with the explicit representation of quadrics, a set of ten coefficients are determined for various three-dimensional surfaces. For each quadric surface, a unique set of two-dimensional curves which serve as a feature set is obtained from the various angles at which the object is intersected with a plane. Based on a discriminant method, each of the curves is classified as a parabola, circle, ellipse, hyperbola, or a line. Each quadric surface is shown to be …

Formant Estimation From Dctc's Using A Feedforward Neural Network, Shubhangi U. Kelkar

Electrical & Computer Engineering Theses & Dissertations

Formants are the natural frequencies of the human vocal tract. Existing methods for estimating formants from speech signals are computationally complex and subject to errors for certain type of speech sounds. This thesis describes a method for estimating vowel formant frequencies from Discrete Cosine Transform Coefficients (DCTC's), a form of cepstral coefficients, using a feedforward neural network with back-propagation training. Experimental results are based on a large multispeaker data base. The results are obtained for both a linear transformation and a feedforward neural network with a nonlinear hidden layer. In general, the neural network transformation is superior to the linear …

An Artificial Neural Approach To The Decomposition Problem, Chandrashekar L. Masti

Electrical & Computer Engineering Theses & Dissertations

The goal of this thesis is to develop an artificial neural approach toward addressing the intractability involved with the decomposition problem. The search for the lattice of substitution property (s. p.) partitions essential to decompositions is cast into the framework of constraint satisfaction. An artificial neural network is developed to provide solutions by performing optimization of a mathematically derived objective function over the problem space. The issue of transitivity is verified to belong to a class of problems beyond the scope of solvability for conventional quadratic-order constraint satisfaction neural networks. A theorem is stated and proved establishing that third-order correlations …