istft#

diffsptk.ISTFT#: alias of InverseShortTimeFourierTransform

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

This is the opposite module to ShortTimeFourierTransform()

Parameters:

frame_lengthint >= 1: Frame length, \(L\).
frame_peirodint >= 1: Frame period, \(P\).
fft_lengthint >= L: Number of FFT bins, \(N\).
centerbool: 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.
window[‘blackman’, ‘hamming’, ‘hanning’, ‘bartlett’, ‘trapezoidal’, ‘rectangular’]: Window type.
norm[‘none’, ‘power’, ‘magnitude’]: Normalization type of window.

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

Compute inverse short-time Fourier transform.

Parameters:

yTensor [shape=(…, T/P, N/2+1)]: Complex spectrum.
out_lengthint or None: Length of output waveform.

Returns:

outTensor [shape=(…, T)]: Reconstructed 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.])

diffsptk.functional.istft(y, *, out_length=None, frame_length=400, frame_period=80, fft_length=512, center=True, window='blackman', norm='power')[source]#

Compute inverse short-time Fourier transform.

Parameters:

yTensor [shape=(…, T/P, N/2+1)]: Complex spectrum.
out_lengthint >= 1 or None: Length of output signal.
frame_lengthint >= 1: Frame length, \(L\).
frame_peirodint >= 1: Frame period, \(P\).
fft_lengthint >= L: Number of FFT bins, \(N\).
centerbool: 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.
window[‘blackman’, ‘hamming’, ‘hanning’, ‘bartlett’, ‘trapezoidal’, ‘rectangular’]: Window type.
norm[‘none’, ‘power’, ‘magnitude’]: Normalization type of window.

Returns:

outTensor [shape=(…, T)]: Waveform.