In this project, i used tensorflow with the help of some other dependencies to create an Audio Classification Algorithm that can distinguish between different speech commands. The commands were in the form of orated words or numbers labelled by the thousands and converted into audio files for preprocessing and training. I created this project to understand the basics of audio classification and how to apply them in real life scenarios.
Librosa for preprocessing, Tensorflow and Sklearn for model creation and training and matplotlib/seaborn for visualization
Use google colab and create two seperate files for preprocessing the data and for training the data. I recommend following this series of youtube tutorials beginning with this one to see the steps i followed to create this project: youtube link
Tensorflow
Librosa
Sklearn