Shape of a 1D Kaiser window:

Shape of a 2D Kaiser window:

Extract the continuous function representing the Kaiser window:

Parameterized Kaiser window:

Evaluate numerically:

Shape of a 1D Kaiser window using a specified parameter:

Translated and dilated Kaiser window:

Variation of the shape as a function of the parameter α:

Shape of a 2D Kaiser window:

Two-dimensional Kaiser window with a circular support:

Discrete Kaiser window of length 15:

Discrete 15×10 2D Kaiser window:

Use the Kaiser window to diminish the effect of signal partitioning when computing the spectrogram:

Create a lowpass FIR filter with cutoff frequency of and length 15:

Apply a Kaiser window to the filter to improve stopband attenuation:

Log-magnitude plot of the power spectra of the two filters:

Filter a white noise signal using the Kaiser window method:

Use a window specification to calculate sample PowerSpectralDensity of an ARMA process:

Calculate the spectrum:

Compare to spectral density calculated without a windowing function:

The plot shows that window smooths the spectral density:

Compare to the theoretical spectral density of the process:

Use a window specification for time series estimation:

Specify window for spectral estimator:

The area under the Kaiser window:

Normalize to create a window with unit area:

Fourier transform of the Kaiser window:

Power spectrum of the Kaiser window:

Fourier transform of the parametrized Kaiser window:

Variation of the magnitude spectrum as a function of the parameter α:

Discrete Kaiser window of length 15:

Normalize so the coefficients add up to 1:

Discrete-time Fourier transform of a normalized discrete Kaiser window of length 15:

Magnitude spectrum:

Power spectra of the default Kaiser and rectangular windows:

Power spectra for three different window lengths:

Power spectra for three different values of the shape parameter α:

Two-dimensional sampling of Kaiser window will use a different parameter for each row of samples when passed as a symbol to Array:

Use a pure function instead: