ahmedabdalkreem / speech-recognition

In this project we deal with audio dataset to make classification between ten audio and make preprocssing in it using Librosa and Scipy then be input of Neural Network Model.

Speech-Recognition

In this project we deal with audio dataset to make classification between ten audio and make preprocssing in it using Librosa and Scipy then be input of Neural Network Model.

What is the goal of project?

The goal of project to make speech recognition to know the different between 10 audio and all the details of project explane in file called Audio classifiction using Deep Learing.

What you will learn before this project?

1. Know collect the audio dataset.
2. Deal with audio read and show it in graph.
3. Learn deal with librosa and scipy library that deal with audio.
4. Know the best to use with audio ==> Librosa.
5. Extraction the deatils of audio using MFCC.
6. Now the best model using neural network.
7. Build your model using deep neural network.
8. Calculate accuracy of model before training.
9. Make function to take audio and return that contain in any class.