User`s guide

Levinson-Durbin

5-266

average (MA) process (or FIR filter) that predicts the next value of a signal

from the current signal sample and a finite number of past samples. In this

case, the input to the block represents the signal’s autocorrelation sequence,

with

r(1) being the zero-lag value, and the output at the block’s A port contains

the coefficients of the predictive MA process (in descending powers of z).

These coefficients solve the optimization problem below.

Again, the output at the block’s

K port contains the corresponding reflection

coefficients,

[k(1) k(2) ... k(n)], for the lattice realization of this FIR

filter. The Autocorrelation LPC block in the Linear Prediction library

implements this autocorrelation-based prediction method.

Algorithm The algorithm requires O(n

) operations, and is thus much more efficient for

large n than standard Gaussian elimination, which requires O(n

) operations.

Dialog Box

Output(s)

The solution representation of Ra = b to output: model coefficients (

A),

reflection coefficients (

K), or both (AandK). For scalar inputs, this

parameter must be set to

Hz() Az() 1 a 2()z

1–

… an 1+()z

n–

+++==

min

{}

ni–

i 1=

∑

–