audio_tools.py 文件源码

def harvest(x, fs):
    f0_floor = 71
    f0_ceil = 800
    target_fs = 8000
    channels_in_octave = 40.
    basic_temporal_positions, temporal_positions = _world_get_temporal_positions(len(x), fs)
    adjusted_f0_floor = f0_floor * 0.9
    adjusted_f0_ceil = f0_ceil * 1.1
    boundary_f0_list = np.arange(1, np.ceil(np.log2(adjusted_f0_ceil / adjusted_f0_floor) * channels_in_octave) + 1) / float(channels_in_octave)
    boundary_f0_list = adjusted_f0_floor * 2.0 ** boundary_f0_list
    y, actual_fs = harvest_get_downsampled_signal(x, fs, target_fs)
    fft_size = 2. ** np.ceil(np.log2(len(y) + np.round(fs / f0_floor * 4) + 1))
    y_spectrum = np.fft.fft(y, int(fft_size))
    raw_f0_candidates = harvest_get_raw_f0_candidates(
        len(basic_temporal_positions),
        boundary_f0_list, len(y), basic_temporal_positions, actual_fs,
        y_spectrum, f0_floor, f0_ceil)

    f0_candidates, number_of_candidates = harvest_detect_official_f0_candidates(raw_f0_candidates)
    f0_candidates = harvest_overlap_f0_candidates(f0_candidates, number_of_candidates)
    f0_candidates, f0_scores = harvest_refine_candidates(y, actual_fs,
            basic_temporal_positions, f0_candidates, f0_floor, f0_ceil)

    f0_candidates, f0_scores = harvest_remove_unreliable_candidates(f0_candidates, f0_scores)

    connected_f0, vuv = harvest_fix_f0_contour(f0_candidates, f0_scores)
    smoothed_f0 = harvest_smooth_f0_contour(connected_f0)
    idx = np.minimum(len(smoothed_f0) - 1, np.round(temporal_positions * 1000)).astype("int32")
    f0 = smoothed_f0[idx]
    vuv = vuv[idx]
    f0_candidates = f0_candidates
    return temporal_positions, f0, vuv, f0_candidates