sgmse

Speech Enhancement and Dereverberation with Diffusion-based Generative Models

This repository contains the official PyTorch implementations for the papers:

• Simon Welker, Julius Richter, Timo Gerkmann, "Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain", ISCA Interspeech, Incheon, Korea, Sept. 2022. [bibtex]
• 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. [bibtex]
• Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann, "Analysing diffusion-based generative approaches versus discriminative approaches for speech restoration", ICASSP, Rhodes Island, Greece, 2023. [bibtex]
• 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 Interspecch, Kos, Greece, Sept. 2024. [bibtex]
• Julius Richter, Danilo de Oliveira, Timo Gerkmann, "Investigating Training Objectives for Generative Speech Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hyderabad, India, April 2025. [bibtex]

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:

• Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann, "StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation", IEEE/ACM Transactions on Audio, Speech, Language Processing, vol. 31, pp. 2724 -2737, 2023. [github]
• Bunlong Lay, Simon Welker, Julius Richter, Timo Gerkmann, "Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement", ISCA Interspeech, Dublin, Ireland, Aug. 2023. [github]

Installation

• Create a new virtual environment with Python 3.11 (we have not tested other Python versions, but they may work).
• Install the package dependencies via pip install -r requirements.txt.
  • Let pip resolve the dependencies for you. If you encounter any issues, please check requirements_version.txt for the exact versions we used.
• If using W&B logging (default):
  • Set up a wandb.ai account
  • Log in via wandb login before running our code.
• If not using W&B logging:
  • Pass the option --nolog to train.py.
  • Your logs will be stored as local CSVLogger logs in lightning_logs/.

Pretrained checkpoints

• For the speech enhancement task, we offer pretrained checkpoints for models that have been trained on the VoiceBank-DEMAND and WSJ0-CHiME3 datasets, as described in our journal paper [2]. You can download them here.
  • SGMSE+ trained on VoiceBank-DEMAND: gdown 1_H3EXvhcYBhOZ9QNUcD5VZHc6ktrRbwQ
  • SGMSE+ trained on WSJ0-CHiME3: gdown 16K4DUdpmLhDNC7pJhBBc08pkSIn_yMPi
• For the dereverberation task, we offer a checkpoint trained on our WSJ0-REVERB dataset. You can download it here.
  • SGMSE+ trained on WSJ0-REVERB: gdown 1eiOy0VjHh9V9ZUFTxu1Pq2w19izl9ejD
  • Note that this checkpoint works better with sampler settings --N 50 --snr 0.33.
• For 48 kHz models [3], we offer pretrained checkpoints for speech enhancement, trained on the EARS-WHAM dataset, and for dereverberation, trained on the EARS-Reverb dataset. You can download them here.
  • SGMSE+ trained on EARS-WHAM: gdown 1t_DLLk8iPH6nj8M5wGeOP3jFPaz3i7K5
  • SGMSE+ trained on EARS-Reverb: gdown 1PunXuLbuyGkknQCn_y-RCV2dTZBhyE3V
• For the investigating training objectives checkpoints [4], we offer the pretrained checkpoints here.
  • M1: wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/icassp2025_gense/checkpoints/m1.ckpt
  • M2: wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/icassp2025_gense/checkpoints/m2.ckpt
  • M3: wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/icassp2025_gense/checkpoints/m3.ckpt
  • M4: Please check our repo for EDM2SE
  • M5: wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/icassp2025_gense/checkpoints/m5.ckpt
  • M6: wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/icassp2025_gense/checkpoints/m6.ckpt
  • M7: wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/icassp2025_gense/checkpoints/m7.ckpt
  • M8: wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/icassp2025_gense/checkpoints/m8.ckpt
• We offer a pretrained checkpoint for the Schrödinger bridge model trained on EARS-WHAM + VB-DMD dataset. You can download it here. The model is trained with: batch_size=16, devices=2, backbone="ncsnpp_v2", loss_type="data_prediction", sde="sbve", sr=16000.
• We provide pretrained checkpoints for SGMSE+ and the SB trained on Singing-ReverbFX here.
  • SGMSE+ (artificial RIR): wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/itg2025-reverbfx/checkpoints/sgmse_artificial_rir_350k.ckpt
  • SGMSE+ (natural RIR): wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/itg2025-reverbfx/checkpoints/sgmse_natural_rir_350k.ckpt
  • SB (artificial RIR): wget https://www2.informatik.uni-hamburg.de/sp/audio/publications/itg2025-reverbfx/checkpoints/sb_artificial_rir_350k.ckpt
  • Please cite the ReverbFX dataset paper, when you make use of the data or the checkpoints:
    bib复制

    @inproceedings{richter2025reverbfx,
      author={Julius Richter and Till Svajda and Timo Gerkmann},
      title={{ReverbFX}: A Dataset of Room Impulse Responses Derived from Reverb Effect Plugins for Singing Voice Dereverberation},
      year={2025},
      booktitle={ITG Conference on Speech Communication},
    }

Usage:

• For resuming training, you can use the --ckpt option of train.py.
• For evaluating these checkpoints, use the --ckpt option of enhancement.py (see section Evaluation below).

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 

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:

• Our journal [2] uses --backbone ncsnpp.
• For the 48 kHz model [3], use --backbone ncsnpp_48k --n_fft 1534 --hop_length 384 --spec_factor 0.065 --spec_abs_exponent 0.667 --sigma-min 0.1 --sigma-max 1.0 --theta 2.0
• Our Interspeech paper [1] uses --backbone dcunet. You need to pass --n_fft 512 to make it work.
  • Also note that the default parameters for the spectrogram transformation in this repository are slightly different from the ones listed in the first (Interspeech) paper (--spec_factor 0.15 rather than --spec_factor 0.333), but we've found the value in this repository to generally perform better for both models [1] and [2].
• For the investigating training objectives paper [4], we use --backbone ncsnpp_v2.
• For the Schrödinger bridge model [4], we use e.g. --backbone ncsnpp_v2 --sde sbve --loss_type data_prediction --pesq_weight 5e-4.

Evaluation

To evaluate on a test set, run

python enhancement.py --test_dir  --enhanced_dir  --ckpt 

to generate the enhanced .wav files, and subsequently run

python calc_metrics.py --test_dir  --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{lemercier2023analysing,
  author={Lemercier, Jean-Marie and Richter, Julius and Welker, Simon and Gerkmann, Timo},
  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Analysing Diffusion-based Generative Approaches Versus Discriminative Approaches for Speech Restoration}, 
  year={2023},
  pages={1-5},
  doi={10.1109/ICASSP49357.2023.10095258}
}

@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 Mod