audio_tools.py 文件源码

def world_synthesis_time_base_generation(temporal_positions, f0, fs, vuv,
        time_axis, default_f0):
    f0_interpolated_raw = interp1d(temporal_positions, f0, kind="linear",
            fill_value="extrapolate")(time_axis)
    vuv_interpolated = interp1d(temporal_positions, vuv, kind="linear",
            fill_value="extrapolate")(time_axis)
    vuv_interpolated = vuv_interpolated > 0.5
    f0_interpolated = f0_interpolated_raw * vuv_interpolated.astype("float32")
    f0_interpolated[f0_interpolated == 0] = f0_interpolated[f0_interpolated == 0] + default_f0
    total_phase = np.cumsum(2 * np.pi * f0_interpolated / float(fs))

    core = np.mod(total_phase, 2 * np.pi)
    core = np.abs(core[1:] - core[:-1])
    # account for diff, avoid deprecation warning with [:-1]
    pulse_locations = time_axis[:-1][core > (np.pi / 2.)]
    pulse_locations_index = np.round(pulse_locations * fs).astype("int32")
    return pulse_locations, pulse_locations_index, vuv_interpolated