User`s guide

Short-Time FFT
5-385
5Short-Time FFT
Purpose Compute a nonparametric estimate of the spectrum using the short-time, fast
Fourier transform (ST-FFT) method.
Library Estimation / Power Spectrum Estimation
Description The Short-Time FFT block computes a nonparametric estimate of the
spectrum. The block averages the squared magnitude of the FFT computed
over windowed sections of the input, and normalizes the spectral average by
the square of the sum of the window samples.
Both an M-by-N frame-based matrix input and an M-by-N sample-based
matrix input are treated as M sequential time samples from N independent
channels. The block computes a separate estimate for each of the N
independent channels and generates an N
fft
-by-N matrix output. When
Inherit FFT length from input dimensions is selected, N
fft
is specified by the
frame size of the input, which must be a power of 2. When
Inherit FFT length
from input dimensions
is not selected, N
fft
is specified as a power of 2 by the
FFT length parameter, and the block zero pads or truncates the input to N
fft
before computing the FFT.
Each column of the output matrix contains the estimate of the corresponding
input column’s power spectral density at N
fft
equally spaced frequency points
in the range [0,F
s
), where F
s
is the signal’s sample frequency. The output is
always sample-based.
The
Number of spectral averages specifies the number of spectra to average.
Setting this parameter to
1 effectively disables averaging.
The
Window type, Stopband ripple, Beta, and Window sampling
parameters all apply to the specification of the window function; see the
reference page for the Window Function block for more details on these four
parameters.
Example The dspstfft demo provides an illustration of using the Short-Time FFT and
Matrix Viewer blocks to create a spectrogram. The
dspsacomp demo compares
the ST-FFT with several other spectral estimation methods.