def plot_signal_and_segmentation(signal, sampling_rate, segments=[]):
  _time = np.arange(0., np.ceil(float(len(signal))) / sampling_rate, 1./sampling_rate )
  if len(_time) > len(signal):
    _time = _time[: len(signal) - len(_time)]

  pylab.subplot(211)

  for seg in segments:

    fc = seg.get("fc", "g")
    ec = seg.get("ec", "b")
    lw = seg.get("lw", 2)
    alpha = seg.get("alpha", 0.4)

    ts = seg["timestamps"]

    # plot first segmentation outside loop to show one single legend for this class
    p = pylab.axvspan(ts[0][0], ts[0][1], fc=fc, ec=ec, lw=lw, alpha=alpha, label = seg.get("title", ""))

    for start, end in ts[1:]:
      p = pylab.axvspan(start, end, fc=fc, ec=ec, lw=lw, alpha=alpha)


  pylab.legend(bbox_to_anchor=(0., 1.02, 1., .102), loc=3,
          borderaxespad=0., fontsize=16, ncol=2)

  pylab.plot(_time, signal)

  pylab.xlabel("Time (s)", fontsize=16)
  pylab.ylabel("Signal Amplitude", fontsize=16)
  pylab.show()

# ช่วงเวลาในแต่ละคลาสที่โมเดลทำนาย
classes = { 0: [(0.00, 2.00), ...], 1: [(2.01, 2.20), ...] }
speech = { "fc" : "r", "ec" : "r", "lw" : 0, "alpha" : 0.4, "title" : "Speech", "timestamps" : classes[1]}
music = { "fc" : "y", "ec" : "y", "lw" : 0, "alpha" : 0.4, "title" : "Music", "timestamps" : classes[0]}

audio, sr = librosa.load(<PATH_TO_AUDIO>)
plot_signal_and_segmentation(audio, sr, [music, speech])