我正在做:
import librosa
D = librosa.stft(samples, n_fft=nperseg,
hop_length=overlap, win_length=nperseg,
window=scipy.signal.windows.hamming)
spect, _ = librosa.magphase(D)
audio_signal = librosa.griffinlim(spect, n_iter=1024,
win_length=nperseg, hop_length=overlap,
window=signal.windows.hamming)
print(audio_signal, audio_signal.shape)
sf.write('test.wav', audio_signal, sample_rate)
它在重建的音频信号中引入了明显的失真。我能做些什么来改善它?