Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Engineering
Representations, Approximations, And Algorithms For Mathematical Speech Processing, Laura R. Suzuki
Representations, Approximations, And Algorithms For Mathematical Speech Processing, Laura R. Suzuki
Theses and Dissertations
Representing speech signals such that specific characteristics of speech are included is essential in many Air Force and DoD signal processing applications. A mathematical construct called a frame is presented which captures the important time-varying characteristic of speech. Roughly speaking, frames generalize the idea of an orthogonal basis in a Hilbert space, Specific spaces applicable to speech are L2(R) and the Hardy spaces Hp(D) for p> 1 where D is the unit disk in the complex plane. Results are given for representations in the Hardy spaces involving Carleson's inequalities (and its extensions), …
An Evaluation Of Frequency Domain Ensemble Averaging To Improve Aircraft Stability Derivative Estimation, Lawrence M. Hoffman
An Evaluation Of Frequency Domain Ensemble Averaging To Improve Aircraft Stability Derivative Estimation, Lawrence M. Hoffman
Theses and Dissertations
This research evaluated a process to improve aircraft stability derivative estimation results. The Have Derivatives process used overlap ensemble averaging in the frequency domain to minimize noise on the original time domain signals. The process estimated average complex frequency response functions that were then transformed back into the time domain as a set of discrete pulse responses with far less noise than the original signals. These clean signals were used in a parameter estimation program to estimate better stability derivatives than were estimated with the original noisy signals. Both simulation and flight test data were used to study the effects …
Channel-Mismatch Compensation In Speaker Identification Feature Selection And Adaptation With Artificial Neural Networks, Edmund A. Fitzgerald
Channel-Mismatch Compensation In Speaker Identification Feature Selection And Adaptation With Artificial Neural Networks, Edmund A. Fitzgerald
Theses and Dissertations
We develop and present results of an artificial neural network (ANN) based compensation technique for mismatched classifier training and testing conditions in speaker identification (SID). One ANN per feature per speaker is trained to perform a mapping of that feature from a corrupted condition to an undistorted condition. Therefore, a classifier trained under one condition may be used to classify data collected under a different condition. Speech utterances from 168 speakers, collected in a studio, and also re-recorded after transmission over telephone networks, are used for developing and testing the method. Peak formant resonant frequencies, their bandwidths, and pitch are …