Systems and Communications Commons^™

Speech Feature Computation For Visual Speech Articulation Training, Stefan Auberg

Electrical & Computer Engineering Theses & Dissertations

A new version of the Visual Speech Articulation Training Aid was implemented which provides real-time visual feedback for speech articulation training. This version was migrated to a Windows Multimedia PC from a previous version which used a Personal Computer (PC) system and additional specialized and expensive custom hardware. This new version will make the system more available to schools and private users. A new method was developed for computing spectral/temporal features which characterize the speech sounds. In addition to the typical frame-based spectral analysis parameters, the new method represents temporal changes of the spectrum with a small number of features. …

Variable Step Size Lms Adaptive Filters With Delayed Coefficient Updating, Guixian Xu

Electrical & Computer Engineering Theses & Dissertations

A new approach to delayed LMS adaptive filtering is presented, which uses a variable step size for coefficient updating to increase convergence speed and improve tracking characteristics. The new algorithm, called delayed variable step size LMS (DVLMS), is explained, analyzed, and simulated to experimentally determine performance characteristics. Three different strategies for adjusting the step size are examined, and their performance is compared. Also, simulation results are presented to show that the proposed DVLMS systems provide faster convergence and lower mis-adjustment than previously proposed DLMS systems.

Adaptive Integration Of Audio And Visual Information Using Discrete And Semi-Continuous Hidden Markov Models In Audiovisual Automatic Speech Recognition, Qin Su

Electrical & Computer Engineering Theses & Dissertations

An audiovisual semi-continuous hidden Markov model (HMM)-based Automatic Speech Recognition (ASR) system and an improved method of integrating audio and visual information in an audiovisual discrete HMM-based ASR system are investigated.

In the audiovisual discrete HMM, an adaptive integration formulation is employed, which incorporates the integration into the HMM at a pre-categorical stage. A visual weighting parameter is determined automatically, which allows the relative contribution of audio and visual information to be adjusted adaptively. Using an adaptive weight, the accuracy increased by 13% compared to the same model with no adaptive weight.

The semi-continuous HMM is a class of models …

An Application Of Neural Networks In Data Communication Real-Time Resource Reallocation, Qing Fan

Electrical & Computer Engineering Theses & Dissertations

This thesis presents an application of artificial neural networks in real-time resource reallocation, a methodology used in the implementation of an intelligent interface node in the Computer Integrated Manufacturing (CIM) environment. In particular, the problem is formulated using a Hopfield neural network model. The real-time reallocation problem is mapped into a two-dimensional matrix of neurons similar to Hopfield and Tank's approach to the traveling salesman problem (TSP) . An energy function is formulated in terms of the hard constraints and the solution cost. The interconnection weights and the input biases are determined by the energy function. It is shown through …

Analysis And Development Of A Switched Capacitor Power Supply, John Richard Hackworth

Electrical & Computer Engineering Theses & Dissertations

The combination of a switched capacitor network and switching power supply techniques can result in a transformer less regulated DC power supply that is small, relatively simple, and efficient. In addition, the output of such a system could be operated over a wide range of common mode voltages. Multiple switched capacitor supplies could be stacked to achieve voltage multiplication.

Although the output of a system of this type is a continuous function, the internal operation must be analyzed in finite time elements. This numerical analysis will be shown in both a mathematical approach and a computer model.

An Investigation To Improve Linear Predictive Vocoder Pulse/Noise Excitation Models, Elizabeth Annella Martina Effer

Electrical & Computer Engineering Theses & Dissertations

The quality of synthetic speech from Linear Predictive (LP) vocoders is known to be degraded due to the lack of detail in the commonly used pulse/noise excitation model. In this investigation, it was hypothesized that this degradation is due to the lack of precise timing information in the pulses and to the constraint that each short-time segment of excitation be either an impulse train or white noise. Accordingly, more complex excitation models were implemented using precise timing from peaks in the residual and a mixture of pulses and noise. Since the LP residual is known to be the perfect excitation …

Design Of Infrasound-Detection System Via Adaptive Lmstde Algorithm, Camille S. Khalaf

Electrical & Computer Engineering Theses & Dissertations

A proposed solution to an aviation safety problem is based on passive detection of turbulent weather phenomena through their infrasonic emission. This thesis describes a system design that is adequate for detection and bearing evaluation of infrasounds. An array of four sensors, with the appropriate hardware, is used for the detection part. Bearing evaluation is based on estimates of time delays between sensor outputs. The generalized cross correlation (GCC), as the conventional time-delay estimation (TOE) method, is first reviewed. An adaptive TUt approach, using the least mean square (LMS) algorithm, is then discussed. A comparison between the two techniques is …