README.md

Learning audio modeling: Audio Classification.

Summary

The purpose of this notebook is to teach myself audio processing from scratch. This notebooks are resources summarizing and showing example of processing techniques, data augmentation and modeling techniques for audio. Those notebooks are highly based on the references cited below and the toy example is a PyTorch implementation of Sath Adam's series of videos.

TODO's:

• Audio Processing Techniques: Review and Summary.
• Toy example: Instrument classification.
  • Data Visualization (fft, bank filters, mfcc).
  • Pre-processing.
  • CNN-modeling.
  • RNN-modeling.

References

Audio Preprocessing

• http://practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/

• https://haythamfayek.com/2016/04/21/speech-processing-for-machine-learning.html

• https://www.youtube.com/watch?v=Z7YM-HAz-IY&list=PLhA3b2k8R3t2Ng1WW_7MiXeh1pfQJQi_P&index=1

Data Augmentation

• https://medium.com/@makcedward/data-augmentation-for-audio-76912b01fdf6

Further reading

• https://arxiv.org/pdf/1810.12832.pdf