Home

Awesome

Speech Enhancement and Dereverberation with Diffusion-based Generative Models

<img src="https://raw.githubusercontent.com/sp-uhh/sgmse/main/diffusion_process.png" width="500" alt="Diffusion process on a spectrogram: In the forward process noise is gradually added to the clean speech spectrogram x0, while the reverse process learns to generate clean speech in an iterative fashion starting from the corrupted signal xT.">

This repository contains the official PyTorch implementations for the papers:

Audio examples and supplementary materials are available on our SGMSE project page, EARS project page, and Investigating training objectives project page.

An interactive demo of generative speech enhancement using a juypter notebook can be found here.

Follow-up work

Please also check out our follow-up work with code available:

Installation

Pretrained checkpoints

Usage:

Training

Training is done by executing train.py. A minimal running example with default settings (as in our paper [2]) can be run with

python train.py --base_dir <your_base_dir>

where your_base_dir should be a path to a folder containing subdirectories train/ and valid/ (optionally test/ as well). Each subdirectory must itself have two subdirectories clean/ and noisy/, with the same filenames present in both. We currently only support training with .wav files.

To see all available training options, run python train.py --help. Note that the available options for the SDE and the backbone network change depending on which SDE and backbone you use. These can be set through the --sde and --backbone options.

Note:

Evaluation

To evaluate on a test set, run

python enhancement.py --test_dir <your_test_dir> --enhanced_dir <your_enhanced_dir> --ckpt <path_to_model_checkpoint>

to generate the enhanced .wav files, and subsequently run

python calc_metrics.py --test_dir <your_test_dir> --enhanced_dir <your_enhanced_dir>

to calculate and output the instrumental metrics.

Both scripts should receive the same --test_dir and --enhanced_dir parameters. The --cpkt parameter of enhancement.py should be the path to a trained model checkpoint, as stored by the logger in logs/.

Citations / References

We kindly ask you to cite our papers in your publication when using any of our research or code:

@inproceedings{welker22speech,
  author={Simon Welker and Julius Richter and Timo Gerkmann},
  title={Speech Enhancement with Score-Based Generative Models in the Complex {STFT} Domain},
  year={2022},
  booktitle={Proc. Interspeech 2022},
  pages={2928--2932},
  doi={10.21437/Interspeech.2022-10653}
}

@article{richter2023speech,
  title={Speech Enhancement and Dereverberation with Diffusion-based Generative Models},
  author={Richter, Julius and Welker, Simon and Lemercier, Jean-Marie and Lay, Bunlong and Gerkmann, Timo},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  volume={31},
  pages={2351-2364},
  year={2023},
  doi={10.1109/TASLP.2023.3285241}
}

@inproceedings{richter2024ears,
  title={{EARS}: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation},
  author={Richter, Julius and Wu, Yi-Chiao and Krenn, Steven and Welker, Simon and Lay, Bunlong and Watanabe, Shinjii and Richard, Alexander and Gerkmann, Timo},
  booktitle={ISCA Interspeech},
  pages={4873--4877},
  year={2024}
}

@inproceedings{richter2025investigating,
  title={Investigating Training Objectives for Generative Speech Enhancement},
  author={Richter, Julius and de Oliveira, Danilo and Gerkmann, Timo},
  booktitle={IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
  year={2025}
}

[1] Simon Welker, Julius Richter, Timo Gerkmann. "Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain", ISCA Interspeech, Incheon, Korea, Sep. 2022.

[2] Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Timo Gerkmann. "Speech Enhancement and Dereverberation with Diffusion-Based Generative Models", IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2351-2364, 2023.

[3] Julius Richter, Yi-Chiao Wu, Steven Krenn, Simon Welker, Bunlong Lay, Shinji Watanabe, Alexander Richard, Timo Gerkmann. "EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation", ISCA Interspeech, Kos, Greece, 2024.

[4] Julius Richter, Danilo de Oliveira, Timo Gerkmann. "Investigating Training Objectives for Generative Speech Enhancement", accepted at IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025.