def invert_spectrogram(X_s, step, calculate_offset=True, set_zero_phase=True):
"""
Under MSR-LA License
Based on MATLAB implementation from Spectrogram Inversion Toolbox
References
----------
D. Griffin and J. Lim. Signal estimation from modified
short-time Fourier transform. IEEE Trans. Acoust. Speech
Signal Process., 32(2):236-243, 1984.
Malcolm Slaney, Daniel Naar and Richard F. Lyon. Auditory
Model Inversion for Sound Separation. Proc. IEEE-ICASSP,
Adelaide, 1994, II.77-80.
Xinglei Zhu, G. Beauregard, L. Wyse. Real-Time Signal
Estimation from Modified Short-Time Fourier Transform
Magnitude Spectra. IEEE Transactions on Audio Speech and
Language Processing, 08/2007.
"""
size = int(X_s.shape[1] // 2)
wave = np.zeros((X_s.shape[0] * step + size))
# Getting overflow warnings with 32 bit...
wave = wave.astype('float64')
total_windowing_sum = np.zeros((X_s.shape[0] * step + size))
win = 0.54 - .46 * np.cos(2 * np.pi * np.arange(size) / (size - 1))
est_start = int(size // 2) - 1
est_end = est_start + size
for i in range(X_s.shape[0]):
wave_start = int(step * i)
wave_end = wave_start + size
if set_zero_phase:
spectral_slice = X_s[i].real + 0j
else:
# already complex
spectral_slice = X_s[i]
# Don't need fftshift due to different impl.
wave_est = np.real(np.fft.ifft(spectral_slice))[::-1]
if calculate_offset and i > 0:
offset_size = size - step
if offset_size <= 0:
print("WARNING: Large step size >50\% detected! "
"This code works best with high overlap - try "
"with 75% or greater")
offset_size = step
offset = xcorr_offset(wave[wave_start:wave_start + offset_size],
wave_est[est_start:est_start + offset_size])
else:
offset = 0
wave[wave_start:wave_end] += win * wave_est[
est_start - offset:est_end - offset]
total_windowing_sum[wave_start:wave_end] += win
wave = np.real(wave) / (total_windowing_sum + 1E-6)
return wave
评论列表
文章目录
