User`s guide

Overlap-Add FFT Filter
5-331
5Overlap-Add FFT Filter
Purpose Implement the overlap-add method of frequency-domain filtering.
Library Filtering / Filter Designs
Description The Overlap-Add FFT Filter block uses an FFT to implement the overlap-add
method, a technique that combines successive frequency-domain filtered
sections of an input sequence.
Valid inputs to this block are 1-D vectors, sample-based vectors, frame-based
vectors, and frame-based full matrices. All outputs are unbuffered into
sample-based row vectors. The length of the output vector is equal to the
number of channels in the input vector. An M-by-1 sample-based input has M
channels, so it would result in a length-M sample-based output vector. An
M-by-1 frame-based input has only one channel, so would result in a 1-by-1
(scalar) output.
The block’s data output rate is M times faster than its data input rate, where
M is the input frame-size. Thus, the block’s data input and output rates are the
same when the inputs are 1-D vectors, sample-based vectors, or frame-based
row vectors. For frame-based column and frame-based full-matrix inputs, the
block’s data output rate is M times greater than the block’s data input rate.
1-D vectors are treated as length-N sample-based vectors, and result in
sample-based length-N row vectors.
The block breaks the scalar input sequence
u, of length nu, into length-L
nonoverlapping data sections,
which it linearly convolves with the filter’s FIR coefficients,
The numerator coefficients for H(z) are specified as a vector by the
FIR
coefficients
parameter. The coefficient vector, b = [b(1) b(2) ... b(n+1)],
can be generated by one of the filter design functions in the Signal Processing
Toolbox, such as
fir1. All filter states are internally initialized to zero.
. . .
u
2LL 3L ceil(nu/L)*L
Hz() Bz() b
1
b
2
z
1–
… b
n 1+
z
n–
+++==