audio_tools.py 文件源码

def run_fft_dct_example():
    random_state = np.random.RandomState(1999)

    fs, d = fetch_sample_speech_fruit()
    n_fft = 64
    X = d[0]
    X_stft = stft(X, n_fft)
    X_rr = complex_to_real_view(X_stft)
    X_dct = fftpack.dct(X_rr, axis=-1, norm='ortho')
    X_dct_sub = X_dct[1:] - X_dct[:-1]
    std = X_dct_sub.std(axis=0, keepdims=True)
    X_dct_sub += .01 * std * random_state.randn(
        X_dct_sub.shape[0], X_dct_sub.shape[1])
    X_dct_unsub = np.cumsum(X_dct_sub, axis=0)
    X_idct = fftpack.idct(X_dct_unsub, axis=-1, norm='ortho')
    X_irr = real_to_complex_view(X_idct)
    X_r = istft(X_irr, n_fft)[:len(X)]

    SNR = 20 * np.log10(np.linalg.norm(X - X_r) / np.linalg.norm(X))
    print(SNR)

    wavfile.write("fftdct_orig.wav", fs, soundsc(X))
    wavfile.write("fftdct_rec.wav", fs, soundsc(X_r))