metadata

language:
  - en
thumbnail: null
tags:
  - audio-to-audio
  - Speech Enhancement
  - Voicebank-DEMAND
  - UNIVERSE
  - UNIVERSE++
  - Diffusion
  - pytorch
  - open-universe
license: apache-2.0
datasets:
  - Voicebank-DEMAND
metrics:
  - SI-SNR
  - PESQ
  - SIG
  - BAK
  - OVRL
model-index:
  - name: universe++
    results:
      - task:
          name: Speech Enhancement
          type: speech-enhancement
        dataset:
          name: DEMAND
          type: demand
          split: test-set
          args:
            language: en
        metrics:
          - name: DNSMOS SIG
            type: sig
            value: '3.493'
          - name: DNSMOS BAK
            type: bak
            value: '4.042'
          - name: DNSMOS OVRL
            type: ovrl
            value: '3.205'
          - name: PESQ
            type: pesq
            value: 3.017
          - name: SI-SDR
            type: si-sdr
            value: 18.629

open-universe: Generative Speech Enhancement with Score-based Diffusion and Adversarial Training

This repository contains the configurations and weights for the UNIVERSE++ and UNIVERSE models implemented in open-universe.

The models were trained on the Voicebank-DEMAND dataset at 16 kHz.

The performance on the test split of Voicebank-DEMAND is given in the following table.

model	si-sdr	pesq-wb	stoi-ext	lsd	lps	OVRL	SIG	BAK
UNIVERSE++	18.624	3.017	0.864	4.867	0.937	3.200	3.489	4.040
UNIVERSE	17.600	2.830	0.844	6.318	0.920	3.157	3.457	4.013

Usage

Start by installing open-universe. We use conda to simplify the installation.

git clone https://github.com/line/open-universe.git
cd open-universe
conda env create -f environment.yaml
conda activate open-universe
python -m pip install .

Then the models can be used as follows.

# UNIVERSE++ (default model)
python -m open_universe.bin.enhance <input/folder> <output/folder> \
  --model line-corporation/open-universe:plusplus

# UNIVERSE
python -m open_universe.bin.enhance <input/folder> <output/folder> \
  --model line-corporation/open-universe:original

Referencing open-universe and UNIVERSE++

If you use these models in your work, please consider citing the following paper.

@inproceedings{universepp,
    authors={Scheibler, Robin and Fujita, Yusuke and Shirahata, Yuma and Komatsu, Tatsuya},
    title={Universal Score-based Speech Enhancement with High Content Preservation},
    booktitle={Proc. Interspeech 2024},
    month=sep,
    year=2024
}

Referencing UNIVERSE

@misc{universe,
    authors={Serr\'a, Joan and Santiago, Pascual and Pons, Jordi and Araz, Oguz R. and Scaini, David},
    title={Universal Speech Enhancement with Score-based Diffusion},
    howpublished={arXiv:2206.03065},
    month=sep,
    year=2022
}