audio_tools.py 文件源码

def d4c_love_train(x, fs, current_f0, current_position, threshold):
    vuv = 0
    if current_f0 == 0:
        return vuv
    lowest_f0 = 40
    current_f0 = max([current_f0, lowest_f0])
    fft_size = int(2 ** np.ceil(np.log2(3. * fs / lowest_f0 + 1)))
    boundary0 = int(np.ceil(100 / (float(fs) / fft_size)))
    boundary1 = int(np.ceil(4000 / (float(fs) / fft_size)))
    boundary2 = int(np.ceil(7900 / (float(fs) / fft_size)))

    waveform = d4c_get_windowed_waveform(x, fs, current_f0, current_position,
            1.5, 2)
    power_spectrum = np.abs(np.fft.fft(waveform, int(fft_size)) ** 2)
    power_spectrum[0:boundary0 + 1] = 0.
    cumulative_spectrum = np.cumsum(power_spectrum)
    if (cumulative_spectrum[boundary1] / cumulative_spectrum[boundary2]) > threshold:
        vuv = 1
    return vuv