audio_tools.py 文件源码

def ltsd_vad(x, fs, threshold=9, winsize=8192):
    # winsize based on sample rate
    # 1024 for fs = 16000
    orig_dtype = x.dtype
    orig_scale_min = x.min()
    orig_scale_max = x.max()
    x = (x - x.min()) / (x.max() - x.min())
    # works with 16 bit
    x = x * (2 ** 15)
    x = x.astype("int32")
    window = sp.hanning(winsize)
    ltsd = LTSD(winsize, window, 5)
    s_vad = ltsd.compute(x)
    # LTSD is 50% overlap, so each "step" covers 4096 samples
    # +1 to cover the extra edge window
    n_samples = int(((len(s_vad) + 1) * winsize) // 2)
    time_s = n_samples / float(fs)
    time_points = np.linspace(0, time_s, len(s_vad))
    time_samples = (fs * time_points).astype(np.int32)
    time_samples = time_samples
    f_vad = np.zeros_like(x, dtype=np.bool)
    offset = winsize
    for n, (ss, es) in enumerate(zip(time_samples[:-1], time_samples[1:])):
        sss = ss - offset
        if sss < 0:
            sss = 0
        ses = es - offset
        if ses < 0:
            ses = 0
        if s_vad[n + 1] < threshold:
            f_vad[sss:ses] = False
        else:
            f_vad[sss:ses] = True
    f_vad[ses:] = False
    x = x.astype("float64")
    x = x / float(2 ** 15)
    x = x * (orig_scale_max - orig_scale_min) + orig_scale_min
    x = x.astype(orig_dtype)
    return x[f_vad], f_vad