asr_lstm_ctc.py 文件源码

def get_audio_feature():
  '''
  ??wav????mfcc???????
  '''

  audio_filename = "audio.wav"

  #??wav?????fs????? audio???
  fs, audio = wav.read(audio_filename)

  #??mfcc??
  inputs = mfcc(audio, samplerate=fs)
  # ???????????????????
  feature_inputs = np.asarray(inputs[np.newaxis, :])
  feature_inputs = (feature_inputs - np.mean(feature_inputs))/np.std(feature_inputs)

  #?????????
  feature_seq_len = [feature_inputs.shape[1]]

  return feature_inputs, feature_seq_len