audio_tools.py 文件源码

def harvest_get_f0_candidate_from_raw_event(boundary_f0,
        fs, y_spectrum, y_length, temporal_positions, f0_floor,
        f0_ceil):
    filter_length_half = int(np.round(fs / boundary_f0 * 2))
    band_pass_filter_base = harvest_nuttall(filter_length_half * 2 + 1)
    shifter = np.cos(2 * np.pi * boundary_f0 * np.arange(-filter_length_half, filter_length_half + 1) / float(fs))
    band_pass_filter = band_pass_filter_base * shifter

    index_bias = filter_length_half
    # possible numerical issues if 32 bit
    spectrum_low_pass_filter = np.fft.fft(band_pass_filter.astype("float64"), len(y_spectrum))
    filtered_signal = np.real(np.fft.ifft(spectrum_low_pass_filter * y_spectrum))
    index_bias = filter_length_half + 1
    filtered_signal = filtered_signal[index_bias + np.arange(y_length).astype("int32")]
    negative_zero_cross = harvest_zero_crossing_engine(filtered_signal, fs)
    positive_zero_cross = harvest_zero_crossing_engine(-filtered_signal, fs)
    d_filtered_signal = filtered_signal[1:] - filtered_signal[:-1]
    peak = harvest_zero_crossing_engine(d_filtered_signal, fs)
    dip = harvest_zero_crossing_engine(-d_filtered_signal, fs)
    f0_candidate = harvest_get_f0_candidate_contour(negative_zero_cross,
            positive_zero_cross, peak, dip, temporal_positions)
    f0_candidate[f0_candidate > (boundary_f0 * 1.1)] = 0.
    f0_candidate[f0_candidate < (boundary_f0 * .9)] = 0.
    f0_candidate[f0_candidate > f0_ceil] = 0.
    f0_candidate[f0_candidate < f0_floor] = 0.
    return f0_candidate