语音－MFCC,Fbank特征提取

• 提取12维MFCC特征和23维FBank

  import librosa
  import numpy as np
  import matplotlib.pyplot as plt
  import librosa.display
  from scipy.fftpack import dct
  
  # 绘制频谱图
  def plot_spectrogram(spec, note):
      fig = plt.figure(figsize=(20, 5))
      heatmap = plt.pcolor(spec)
      fig.colorbar(mappable=heatmap)
      plt.xlabel('Time(s)')
      plt.ylabel(note)
      plt.tight_layout()
  
  #preemphasis config 
  alpha = 0.97 #滤波器系数（α）
  
  # Enframe config
  frame_len = 400      # 25ms, fs=16kHz
  frame_shift = 160    # 10ms, fs=15kHz
  fft_len = 512        #参与FFT运算的512个数据
  
  # Mel filter config
  num_filter = 23
  num_mfcc = 12
  
  # Read wav file
  wav, fs = librosa.load('./test.wav', sr=None) #Librosa默认的采样率是22050，如果需要读取原始采样率，需要设定参数sr=None
  ##plt.plot(wav)
  ##plt.show()
  #print(fs)
  plt.figure()
  librosa.display.waveplot(wav, fs)
  plt.show()
  # Pre-Emphasis
  def preemphasis(signal, coeff=alpha):