timitphonemerec.py 文件源码

def _mfcc_and_labels(audio, labels):
  """ Convert to MFCC features and corresponding (interpolated) labels.

  Returns:
    A tuple, `(mfcc_features, mfcc_labels)`. A 1-D float array and a 1-D int
      array, both with the same shape.
  """
  mfcc_sample_rate = 100.0
  winfunc = lambda x: np.hamming(x)
  mfcc_features = python_speech_features.mfcc(audio, samplerate=timit.SAMPLE_RATE, winlen=0.025,
                                              winstep=1.0/mfcc_sample_rate, lowfreq=85.0,
                                              highfreq=timit.SAMPLE_RATE/2, winfunc=winfunc)
  t_audio = np.linspace(0.0, audio.shape[0] * 1.0 / timit.SAMPLE_RATE, audio.size, endpoint=False)
  t_mfcc = np.linspace(0.0, mfcc_features.shape[0] * 1.0 / mfcc_sample_rate, mfcc_features.shape[0], endpoint=False)
  interp_func = scipy.interpolate.interp1d(t_audio, labels, kind='nearest')
  mfcc_labels = interp_func(t_mfcc)
  return mfcc_features, mfcc_labels