https://github.com/qzed/noisereduce
Experimental Project on Noise Reduction.
https://github.com/qzed/noisereduce
Last synced: 3 months ago
JSON representation
Experimental Project on Noise Reduction.
- Host: GitHub
- URL: https://github.com/qzed/noisereduce
- Owner: qzed
- License: mit
- Created: 2019-06-23T22:16:57.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2022-09-17T02:14:51.000Z (over 3 years ago)
- Last Synced: 2025-04-09T16:52:55.891Z (about 1 year ago)
- Language: Rust
- Homepage:
- Size: 7.32 MB
- Stars: 6
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Noisereduce
Modular implementation of real-time capable adaptive noise reduction algorithms.
Incorporates MMSE, log-MMSE, OM-LSA and MCRA algorithms based on _Speech Enhancement Using a Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator_ (Ephraim and Malah), _Speech Enhancement Using a Minimum Mean-Square Error Log-Spectral Amplitude Estimator_ (Ephraim and Malah), and _Speech Enhancement for Non-Stationary Noise Environments_ (Cohen and Berdugo).
Project for the Speech Signal Processing and Speech Enhancement course, summer term 2019, University of Stuttgart.
Algorithms can be specified via parameter-files (see `params/` for examples). The main utility can be run via
```
cargo run --release --bin noisereduce -- -p
```
Feel free to have a look at the corresponding [slides][slides] and [paper][paper].
[paper]: https://nbviewer.jupyter.org/github/qzed/noisereduce/blob/master/paper/Real-Time%20capable%20Noise%20Reduction%20Methods.pdf
[slides]: https://nbviewer.jupyter.org/github/qzed/noisereduce/blob/master/paper/Slides.pdf