audio_tools.py 文件源码

def run_ltsd_example():
    fs, d = fetch_sample_speech_tapestry()
    winsize = 1024
    d = d.astype("float32") / 2 ** 15
    d -= d.mean()

    pad = 3 * fs
    noise_pwr = np.percentile(d, 1) ** 2
    noise_pwr = max(1E-9, noise_pwr)
    d = np.concatenate((np.zeros((pad,)) + noise_pwr * np.random.randn(pad), d))
    _, vad_segments = ltsd_vad(d, fs, winsize=winsize)
    v_up = np.where(vad_segments == True)[0]
    s = v_up[0]
    st = v_up[-1] + int(.5 * fs)
    d = d[s:st]

    bname = "tapestry.wav".split(".")[0]
    wavfile.write("%s_out.wav" % bname, fs, soundsc(d))