Audio Feature: MFCCgram
References
  1. http://librosa.github.io/librosa/generated/librosa.core.stft.html
  2. http://librosa.github.io/librosa/generated/librosa.filters.mel.html
  3. http://librosa.github.io/librosa/generated/librosa.core.power_to_db.html
  4. https://docs.scipy.org/doc/scipy/reference/generated/scipy.fftpack.dct.html
  5. http://librosa.github.io/librosa/generated/librosa.feature.mfcc.html
  6. https://en.wikipedia.org/wiki/Short-time_Fourier_transform
  7. https://en.wikipedia.org/wiki/Mel_scale
  8. https://en.wikipedia.org/wiki/Decibel
  9. https://en.wikipedia.org/wiki/Discrete_cosine_transform
  10. https://en.wikipedia.org/wiki/Mel-frequency_cepstrum
  11. Zheng, Fang, Guoliang Zhang, and Zhanjiang Song. "Comparison of different implementations of MFCC." Journal of Computer science and Technology 16.6 (2001): 582-589.
  12. Davis, Steven B., and Paul Mermelstein. "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences." Readings in speech recognition. 1990. 65-74.