Inter-SubNet

The official PyTorch implementation of "Inter-SubNet: Speech Enhancement with Subband Interaction", accepted by ICASSP 2023.

📜[Full Paper] ▶[Demo] 💿[Checkpoint]

Requirements

• Linux or macOS

• python>=3.6

• Anaconda or Miniconda

• NVIDIA GPU + CUDA CuDNN (CPU can also be supported)

Environment && Installation

Install Anaconda or Miniconda, and then install conda and pip packages:

# Create conda environment
conda create --name speech_enhance python=3.8
conda activate speech_enhance

# Install conda packages
# Check python=3.8, cudatoolkit=10.2, pytorch=1.7.1, torchaudio=0.7
conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch
conda install tensorboard joblib matplotlib

# Install pip packages
# Check librosa=0.8
pip install Cython
pip install librosa pesq pypesq pystoi tqdm toml colorful mir_eval torch_complex

# (Optional) If you want to load "mp3" format audio in your dataset
conda install -c conda-forge ffmpeg

Quick Usage

Clone the repository:

git clone https://github.com/RookieJunChen/Inter-SubNet.git
cd Inter-SubNet

Download the pre-trained checkpoint, and input commands:

source activate speech_enhance
python -m speech_enhance.tools.inference \
  -C config/inference.toml \
  -M $MODEL_DIR \
  -I $INPUT_DIR \
  -O $OUTPUT_DIR

Start Up

Clone

git clone https://github.com/RookieJunChen/Inter-SubNet.git
cd Inter-SubNet

Data preparation

Train data

Please prepare your data in the data dir as like:

• data/DNS-Challenge/DNS-Challenge-interspeech2020-master/
• data/DNS-Challenge/DNS-Challenge-master/

and set the train dir in the script run.sh.

Then:

source activate speech_enhance
bash run.sh 0   # peprare training list or meta file

Test data

Please prepare your test cases dir like: data/test_cases_<name>, and set the test dir in the script run.sh.

Training

First, you need to modify the various configurations in config/train.toml for training.

Then you can run training:

source activate speech_enhance
bash run.sh 1   

Inference

After training, you can enhance noisy speech. Before inference, you first need to modify the configuration in config/inference.toml.

You can also run inference:

source activate speech_enhance
bash run.sh 2

Or you can just use inference.sh:

source activate speech_enhance
bash inference.sh

Eval

Calculating objective metrics (SI_SDR, STOI, WB_PESQ, NB_PESQ, etc.) :

bash metrics.sh

For test set without reference, you can obtain subjective scores (DNS_MOS and NISQA, etc) through DNSMOS and NISQA.

Citation

If you find our work useful in your research, please consider citing:

@inproceedings{chen2023inter,
  title={Inter-Subnet: Speech Enhancement with Subband Interaction},
  author={Chen, Jun and Rao, Wei and Wang, Zilin and Lin, Jiuxin and Wu, Zhiyong and Wang, Yannan and Shang, Shidong and Meng, Helen},
  booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={1--5},
  year={2023},
  organization={IEEE}
}