The code implements the Deep CNN model described in Salamon and Bello's paper for Environmental Sound Classification on Urbansound8k dataset
The code is Divided into 2 parts:
1-Data processing
2-Training Model
Download the Urbansound8k data from the following (or any other working) link 'https://wp.nyu.edu/sonyc/resources/' and preprocess the data so that it is converted into Log Mel Spectrograms using the code. Once done, train the 5 layer CNN model by this data using the 2nd code.