https://github.com/nglehuy/sasegan
Self-Attention Generative Adversarial Network for Speech Enhancement using Tensorflow 2
https://github.com/nglehuy/sasegan
sasegan segan selfattention-segan speech-enhancement
Last synced: about 2 months ago
JSON representation
Self-Attention Generative Adversarial Network for Speech Enhancement using Tensorflow 2
- Host: GitHub
- URL: https://github.com/nglehuy/sasegan
- Owner: nglehuy
- License: apache-2.0
- Created: 2020-09-07T14:56:40.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2021-01-30T07:34:25.000Z (over 4 years ago)
- Last Synced: 2025-04-27T17:39:58.944Z (6 months ago)
- Topics: sasegan, segan, selfattention-segan, speech-enhancement
- Language: Python
- Homepage:
- Size: 90.8 KB
- Stars: 16
- Watchers: 2
- Forks: 6
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
SASEGAN
Self Attention GAN for Speech Enhancement in Tensorflow 2
This is the TensorFlow 2 Version of Self-Attention Generative Adversarial Network for Speech Enhancement. These models can be converted to TFLite :smile:
## :yum: Supported Models
- **SEGAN** (Refer to [https://github.com/santi-pdp/segan](https://github.com/santi-pdp/segan)), see [examples/segan](./examples/segan)
- **SASEGAN** (Refer to [https://github.com/pquochuy/sasegan](https://github.com/pquochuy/sasegan)), see [examples/sasegan](./examples/sasegan)
## Setup Environment and Datasets
Install tensorflow: `pip3 install tensorflow` or `pip3 install tf-nightly` (for using tflite)
Install packages: `pip3 install .`
For **setting up datasets**, see [datasets](sasegan/datasets/README.md)
To enable XLA, run `TF_XLA_FLAGS=--tf_xla_auto_jit=2 $python_train_script`
Clean up: `python3 setup.py clean --all` (this will remove `/build` contents)
## Training & Testing
**Example YAML Config Structure**
```yaml
speech_config: ...
model_config: ...
decoder_config: ...
learning_config:
augmentations: ...
dataset_config:
train_paths: ...
eval_paths: ...
test_paths: ...
tfrecords_dir: ...
optimizer_config: ...
running_config:
batch_size: 8
num_epochs: 20
outdir: ...
log_interval_steps: 500
```
See [examples](./examples/) for some running scripts.
## References
```
@article{phan2020sasegan,
title={Self-Attention Generative Adversarial Network for Speech Enhancement},
author={H. Phan, Hu. L. Nguyen, O. Y. Chén, P. Koch, N. Q. K. Duong, I. McLoughlin, and A. Mertins},
journal={arXiv preprint arXiv:2010.09132},
year={2020}
}
```
1. [Speech Enhancement GAN](https://github.com/santi-pdp/segan)
2. [Improving GANs for Speech Enhancement](https://github.com/pquochuy/idsegan)
3. [Self Attention GAN](https://github.com/brain-research/self-attention-gan)
## Contact
Huy Le Nguyen
Email: nlhuy.cs.16@gmail.com