Main Content

本页对应的英文页面已更新,但尚未翻译。 若要查看最新内容,请点击此处访问英文页面。

信号建模

线性预测、自回归 (AR) 模型、Yule-Walker、Levinson-Durbin

Signal Processing Toolbox™ 提供参数化建模方法,可让您估计描述信号、系统或过程的有理传递函数。使用信号的已知信息来查找对其建模的线性系统的系数。使用 Prony 和 Steiglitz-McBride ARX 模型逼近给定的时域脉冲响应。找到与给定复频率响应匹配的模拟或数字传递函数。使用线性预测滤波器对共振建模。

函数

全部展开

corrmtxData matrix for autocorrelation matrix estimation
levinsonLevinson-Durbin recursion
lpcLinear prediction filter coefficients
rlevinsonReverse Levinson-Durbin recursion
schurrcCompute reflection coefficients from autocorrelation sequence
xcorr互相关
xcov互协方差
ac2polyConvert autocorrelation sequence to prediction polynomial
ac2rcConvert autocorrelation sequence to reflection coefficients
is2rcConvert inverse sine parameters to reflection coefficients
lar2rcConvert log area ratio parameters to reflection coefficients
lsf2polyConvert line spectral frequencies to prediction filter coefficients
poly2acConvert prediction filter polynomial to autocorrelation sequence
poly2lsfConvert prediction filter coefficients to line spectral frequencies
poly2rcConvert prediction filter polynomial to reflection coefficients
rc2acConvert reflection coefficients to autocorrelation sequence
rc2isConvert reflection coefficients to inverse sine parameters
rc2larConvert reflection coefficients to log area ratio parameters
rc2polyConvert reflection coefficients to prediction filter polynomial
arburgAutoregressive all-pole model parameters — Burg’s method
arcovAutoregressive all-pole model parameters — covariance method
armcovAutoregressive all-pole model parameters — modified covariance method
aryuleAutoregressive all-pole model parameters — Yule-Walker method
invfreqsIdentify continuous-time filter parameters from frequency response data
invfreqzIdentify discrete-time filter parameters from frequency response data
pronyProny method for filter design
stmcbCompute linear model using Steiglitz-McBride iteration

主题

Linear Prediction and Autoregressive Modeling

Compare two methods for determining the parameters of a linear filter: autoregressive modeling and linear prediction.

AR Order Selection with Partial Autocorrelation Sequence

Assess the order of an autoregressive model using the partial autocorrelation sequence.

Parametric Modeling

Study techniques that find the parameters for a mathematical model describing a signal, system, or process.

Prediction Polynomial

Obtain the prediction polynomial from an autocorrelation sequence. Verify that the resulting prediction polynomial has an inverse that produces a stable all-pole filter.

特色示例