This repo contains code for the paper CNN-based Learnable Gammatone Filterbank and Equal-loudness Normalization for Environmental Sound Classification.
The models were trained and using TITAN X (Pascal) gpus. All models were developed and tested in
Python 2.7.6
TensorFlow 1.11.0
ESC-50 dataset is necessary to be downloaded and placed in ./Data/
cd Data
wget https://github.com/karoldvl/ESC-50/archive/master.zip
unzip master.zip
rm master.zip
cd ..
python data_augm.py
rm Data/ESC-50-master/audio_da/*.jams
python data_prep.py
python run.py
to be appeared