istft#

diffsptk.ISTFT#: alias of InverseShortTermFourierTransform

class diffsptk.InverseShortTermFourierTransform(frame_length, frame_period, fft_length, *, center=True, norm='power', window='blackman')[source]#

This is the opposite module to ShortTermFourierTransform()

Parameters:

frame_lengthint >= 1 [scalar]: Frame length, \(L\).
frame_peirodint >= 1 [scalar]: Frame period, \(P\).
fft_lengthint >= L [scalar]: Number of FFT bins, \(N\).
centerbool [scalar]: If True, assume that the center of data is the center of frame, otherwise assume that the center of data is the left edge of frame.
norm[‘none’, ‘power’, ‘magnitude’]: Normalization type of window.
window[‘blackman’, ‘hamming’, ‘hanning’, ‘bartlett’, ‘trapezoidal’, ‘rectangular’]: Window type.

forward(y, out_length=None)[source]#

Compute inverse short-term Fourier transform.

Parameters:

yTensor [shape=(…, T/P, N/2+1)]: Complex spectrum.

Returns:

xTensor [shape=(…, T)]: Waveform.

Examples

>>> x = diffsptk.ramp(1, 3)
>>> x
tensor([1., 2., 3.])
>>> stft_params = {"frame_length": 3, "frame_period": 1, "fft_length": 8}
>>> stft = diffsptk.STFT(**stft_params, out_format="complex")
>>> istft = diffsptk.ISTFT(**stft_params)
>>> y = istft(stft(x), out_length=3)
>>> y
tensor([1., 2., 3.])