Generate an audio signal, assuming a cellular automaton evolution to be the magnitude spectrum:

Reconstruct a signal from a magnitude spectrum:

Construct an Audio object from an Image:

Compute the spectrogram of the resulting signal:

The partition size must match the value inferred from the input data:

The inferred partition size is 2×(size-1), where size is the second dimension of the input matrix:

By default, the partition offset is of the inferred partition size:

Specify a different partition offset:

Specify a smoothing window:

Reconstruct an Audio object from its magnitude spectrum:

Construct an Audio object from image data:

Convert the image to grayscale and rotate appropriately:

Reconstruct the signal with the assumption that the image was its spectrogram:

Compute the spectrogram of the resulting signal:

Compute the spectrogram of a signal and its approximate inverse:

Compute the short-time Fourier transform:

Discard the redundant part and take the absolute value to get the magnitude spectrogram:

Use InverseSpectrogram to compute the approximated inverse of the spectrogram:

The partition size must match the value inferred for the input data:

The inferred partition size is 2×(size-1), where size is the second dimension of the input matrix:

Signal reconstruction cannot be done with other partition sizes: