https://github.com/google-research/sound-separation

https://github.com/google-research/sound-separation

Last synced: 3 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/google-research/sound-separation
• Owner: google-research
• License: apache-2.0
• Created: 2020-03-03T05:55:09.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2024-10-02T16:41:12.000Z (3 months ago)
• Last Synced: 2025-01-05T19:02:18.615Z (10 days ago)
• Language: Python
• Size: 60.7 MB
• Stars: 659
• Watchers: 27
• Forks: 119
• Open Issues: 16
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-speech-enhancement - [Code
• awesome-python-audio - pydsm
• StarryDivineSky - google-research/sound-separation

README

        
# Sound Separation

Open-source datasets and deep learning models for separating sounds.

## Datasets

* [Free Universal Sound Separation (FUSS)](https://github.com/google-research/sound-separation/blob/master/datasets/fuss/FUSS_license_doc/README.md).

* [Audio from YFCC100M videos for mixture-invariant training (MixIT)](https://github.com/google-research/sound-separation/blob/master/datasets/yfcc100m/README.md).

* [Audio-visual YFCC100M with annotations for on-screen sound separation with AudioScope](https://github.com/google-research/sound-separation/blob/master/datasets/audioscope/README.md).

* [Audio-visual YFCC100M with annotations for on-screen sound separation with AudioScopeV2](https://github.com/google-research/sound-separation/blob/master/datasets/audioscope-v2/README.md).

* [Synthetic AMI for speech separation in meeting room scenarios](https://github.com/google-research/sound-separation/blob/master/datasets/synthetic_ami/README.md).

## Models

* [Free Universal Sound Separation (FUSS) baseline separation model](https://github.com/google-research/sound-separation/tree/master/models/dcase2020_fuss_baseline/README.md).

* [Universal unsupervised separation models using mixture invariant training (MixIT)](https://github.com/google-research/sound-separation/tree/master/models/neurips2020_mixit/README.md).

* [Unsupervised separation models for birds using mixture invariant training (MixIT)](https://github.com/google-research/sound-separation/tree/master/models/bird_mixit/README.md).