From a44f9df6e0f7bdb3a92f9316009e09f4458693f4 Mon Sep 17 00:00:00 2001
From: Simon <simon.leglaive@gmail.com>
Date: Wed, 29 Apr 2020 15:20:10 +0200
Subject: [PATCH] update readme

---
 README.md | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 74 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 6c0355c..1abbcd4 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,74 @@
-# To Complete
\ No newline at end of file
+# A Recurrent Variational Autoencoder for Speech Enhancement
+
+This repository contains the implementation of the speech enhancement method proposed in:
+
+>S. Leglaive, X. Alameda-Pineda, L. Girin, R. Horaud, [A Recurrent Variational Autoencoder for Speech Enhancement](https://hal.archives-ouvertes.fr/hal-02329000/document), in Proc. of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2020.
+
+Audio examples are available [here](https://sleglaive.github.io/demo-icassp2020.html).
+
+If you use this code, please cite the above-mentioned paper ([Bibtex](https://hal.archives-ouvertes.fr/hal-02329000v1/bibtex)).
+
+## Repository structure
+
+```bash
+.
+├── audio
+│   ├── mix_qut_wsj0.wav
+│   ├── mix_sunrise.wav
+│   └── mix_thierry_roland.wav
+├── environment.yml
+├── LICENSE.txt
+├── main.py
+├── README.md
+├── saved_model
+│   ├── WSJ0_2019-07-15-10h01_RVAE_BRNNenc_BRNNdec_latent_dim=16
+│   │   ├── final_model_RVAE_epoch145.pt
+│   │   ├── loss.pdf
+│   │   ├── loss_RVAE.pckl
+│   │   ├── parameters.pckl
+│   │   └── parameters.txt
+│   ├── WSJ0_2019-07-15-10h14_RVAE_RNNenc_RNNdec_latent_dim=16
+│   │   ├── final_model_RVAE_epoch121.pt
+│   │   ├── loss.pdf
+│   │   ├── loss_RVAE.pckl
+│   │   ├── parameters.pckl
+│   │   └── parameters.txt
+│   └── WSJ0_2019-07-15-10h21_FFNN_VAE_latent_dim=16
+│       ├── final_model_RVAE_epoch65.pt
+│       ├── loss.pdf
+│       ├── loss_RVAE.pckl
+│       ├── parameters.pckl
+│       └── parameters.txt
+├── SE_algorithms.py
+└── training
+    ├── speech_dataset.py
+    ├── train_BRNN_WSJ0.py
+    ├── train_FFNN_WSJ0.py
+    ├── train_RNN_WSJ0.py
+    └── VAEs.py
+```
+
+## Python files
+
+* ```main.py```: Main script to run the speech enhancement algorithms. If you just want to test the method quickly, run this script. Input and output audio files are located in the ```audio``` folder.
+
+* ```SE_algorithms.py```: Implementation of the speech enhancement algorithms (MCEM, PEEM, VEM).
+
+* ```./training/speech_dataset.py```: Custom Pytorch dataset for training.
+
+* ```./training/VAEs.py```: Pytorch implementation of the FFNN, RNN and BRNN variational autoencoders (VAEs).
+
+* ```./training/train_FFNN_WSJ0.py```: Script to train the FFNN VAE.
+
+* ```./training/train_RNN_WSJ0.py```: Script to train the RNN VAE.
+
+* ```./training/train_BRNN_WSJ0.py```: Script to train the BRNN VAE.
+
+
+## Conda environment
+
+```environment.yml``` describes the conda environment that was used for the experiments.
+
+## License
+
+GNU Affero General Public License (version 3), see ```LICENSE.txt```.
\ No newline at end of file
-- 
GitLab