(3.235.108.188) 您好!臺灣時間:2021/02/27 03:31
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:陳柏誠
研究生(外文):Chen, Po-Cheng
論文名稱:在高斯/非高斯雜訊下之適應式自迴歸模型建立:演算法及應用
論文名稱(外文):Adaptive AR Modeling in Gaussian/ Non-Gaussian Noise:Algorithms and Applications
指導教授:吳文榕
指導教授(外文):Wu Wen-Rong
學位類別:博士
校院名稱:國立交通大學
系所名稱:電信工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:1998
畢業學年度:86
語文別:中文
論文頁數:124
中文關鍵詞:高斯雜訊非高斯雜訊自迴歸模型最小平均平方差卡門濾波器
外文關鍵詞:Gaussian NoiseNon-Gaussian NoiseAutoregressive ModelLeast Mean Squre ErrorKalman Filter
相關次數:
  • 被引用被引用:0
  • 點閱點閱:341
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
適應式自迴歸模型建立已廣泛地應用在訊號處理的領域上。自 迴歸
模型的係數可以使用最小平均平方差(LMS)預測誤差濾波器求 出已廣為
人知。然而當輸入訊號受相加性白雜訊干擾時,此濾波器 將求出有偏差
的值。在本論文中我們提出一類新的適應式濾波器來 解決這一個問題。
這類濾波器名為ρ-LMS濾波器,是由估計理論導 出。主要的方法是對輸
入及誤差訊號加以濾波,再將結果輸入LMS 濾波器。由於雜訊減小,偏
差問題也相對地減小。ρ-LMS濾波器在 高斯雜訊下是線性的。而在非高
斯的雜訊下是呈非線性。由於廣泛 性的非高斯濾波問題非常困難,因此
我們只考慮機率分佈可被高斯 和逼近的雜訊。線性及非線性ρ-LMS濾波
器的一階及二階統計特性 的理論值亦在本論文中導出。一個由牛頓法導
出的快速演算法用來 加速ρ-LMS濾波器的收斂速度,因而導出了快速牛
頓ρ-LMS濾波 器。另外ρ-LMS濾波器亦能輸出濾波後的結果,這個重
要性質是其 他LMS型式的濾波器所沒有的。換言之自迴歸模型建立及濾
波可以 整合在一濾波器。當訊號為高斯時,線性的ρ-LMS濾波行為
像卡 門濾波器。而當訊號為非高斯時,非線性的ρ-LMS濾波器像馬氏濾
波器。本論文提出的濾波器亦應用在弦波加強及主動式迴音消除上,並有
令人滿意的結果。至於在濾波方面,我們有其他方法處理偏差 問題。我
們可以使用有偏差的驅動雜訊變異數去補償偏差係數所造 成的影響。當
自迴歸階數不高時,此法可以有不錯的次佳結果。我 們將此結果應用在
語音加強上。有雜訊的語音首先分解成次頻訊號,然後次頻訊號被模擬成
低階自迴歸模型,因此低階的卡門濾波器可 用來加強這些訊號,加強後
的次頻訊號最後被合成加強的全頻語音。在自迴歸係數的處理上,只使用
一般的預測誤差濾波器來估計。卡 門濾波器在偏差係數下的工作效能亦
在本文中有分析。此法不只降 低了運算量亦有不錯的效能。
Adaptive autoregressive (AR) modeling is widely used in
signal processingIt is well-known that the coefficients of an AR
model can be easily obtained using an LMS prediction error
filter. However, this filter givesa biased solution when the
input signal is corrupted by additive white noise.In this
thesis, we propose a new class of adaptive filter to solve the
problem. This class of filters, known as the ρ-LMS filter,
is derived fromthe estimation theory. The main idea is to filter
the noisy input and error signal and then use the results in
the LMS algorithm. Since the noise level is reduced, the bias
problem will consequently be reduced. The ρ-LMS filter is
linear when the noise is Gaussian, however, it becomes
nonlinear when the noise is non-Gaussian. Since the general
non-Gaussian filtering is difficult, we only consider the case
where the noise distribution can be approximated by a Gaussian
sum. Theoretical analysis of the first- and second-order
statistics for the linear and nonlinear ρ-LMS filters are
also presented. A fast algorithm derived from the Newton method
is developed to accelerate the convergence rate of ρ-LMS
filters. This leads to the fast ρ-LMS-Newton filters. Asa by-
product, the ρ-LMS filter can output filtered results. This is
animportant property not shared by other LMS-type filters. In
other words,AR modeling and filtering are combined in a single
filter. The linear ρ-LMS filter can act like a Kalman filter
when noise is Gaussian, and the nonlinear ρ-LMS filter can act
like a Masreliez''s filter when noise isnon-Gaussian. The
proposed filters are then applied in line enhancement and active
noise cancellation and satisfactory results are observed. As far
asfiltering concern, there is another way to deal with the bias
problem. We canuse a biased driving noise variance to compensate
for the effect caused by the biased AR coefficients. When the AR
order is low, this approach can yield a good suboptimal result.
We use this method in speech enhancement.Noisy speech is first
decomposed into subbbands. Subband signals are then modeled as
low-order AR process, such that low-order Kalman filter can be
applied to enhance subband signals. Enhanced subband signals are
finallycombined to form the enhanced fullband speech. To
identify AR coefficients,the conventional prediction-error
filters are used. The performance ofthe Kalman filter with
biased parameters is analyzed. This approach not only greatly
reduces the computational complexity, but also achieves good
performance.
Cover
Chinese Abstract
English Abstract
Acknowledgement
Contents
List of Tables
List of figures
1 Introduction
2 The Problem of AR Modeling
2.1 The AR Model
2.2 The LMS Prediction Error Filter
2.3 The Bias Problem
3 AR Modeling in White Garssian Noise
3.1 The γ-LMS Filter
3.2 The ρ-LMS Filter
3.3 The Fast ρ-LMS-Newton Algorithm
3.4 Simulations
4 AR Modeling in White Non-Gaussian Noise
4.1 The pk Function for Non-Gaussian Noise
4.2 Estimation of σ2εk
4.3 The Convergence Analysis
4.4 Simulations
5 Adaptive Line Enhancer
5.1 Formulation
5.2 The LMS Prediction Error Filter for Noise-free Sinusoidal Signals
5.3 The γ-LMS Filter in Noisy Sinusoidal Signal
5.4 Simulations
6 Active Noise Cancellation
6.1 System Formulation
6.2 Oppenheim''s Method
6.3 The Normalized ρ-LMS Algorithm
6.4 Performance Analysis
6.5 Simulations
7 Subband Kalman Filtering for Speech Enhancement
7.1 INtroduction
7.2 Conventional Kalman Filtering
7.3 Subband Kalman Filtering
7.4 Performance Analysis
7.5 Simulations
8 Conclusions and Further Works
Bibliography
Appendix A
Appendix B
Vita
Publications List
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔