A major concern in audio processing is the reduction or dampening of white noise. Any technique for noise reduction must maintain the musical integrity of the signal. In audio signal processing, thresholding wavelet coefficients is a well established technique for noise reduction. This technique is also an established statistical procedure for generating a nonparametric regression. The primary objective of my work is to explore the use of statistical based procedures in audio processing.
Two general threshold rules and four threshold selection procedures are defined and explored. The bias, variance, and risk of the threshold rules are used as points of comparison. These concepts are expanded and used to develop a modeling procedure. Since the model is valid for a large class of signals, the model may be applied in a variety of fields. The particular application considered is the reduction of noise in digital audio signals. Both musical recordings and artificially generated signals are used to demonstrate the model. The final results are compared with a parametric model.
|School:||California State University, Long Beach|
|School Location:||United States -- California|
|Source:||MAI 47/05M, Masters Abstracts International|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be