qzed / noisereduce

Experimental Project on Noise Reduction.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

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 <parameter-file.yml> <input.wav> <output.wav>

Feel free to have a look at the corresponding slides and paper.

About

Experimental Project on Noise Reduction.

License:MIT License


Languages

Language:Rust 100.0%