General Speech Restoration

Different implementations of "Weighted Prediction Error" for speech dereverberation

The official repo of NBC & SpatialNet for multichannel speech separation, denoising, and dereverberation

Control adaptive filters with neural networks.

The code for multi-channel source separation and dereverberation such as FastMNMF1, FastMNMF2, and AR-FastMNMF2.

A speech dereverberation algorithm, also called wpe

A UNIFIED SPEECH ENHANCEMENT FRONT-END FOR ONLINE DEREVERBERATION, ACOUSTIC ECHO CANCELLATION, AND SOURCE SEPARATION

Machine and Deep Learning models for speech dereverberation

A curated list of awesome Speech Enhancement papers, libraries, datasets, and other resources.

Official PyTorch implementation of "RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function" [ICASSP2024]

This is a single channel speech dereverberation method based on DOI: 10.1109/TSA.2005.858066; implemented in MATLAB

No description provided.

Official PyTorch implementation of 'VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification' [IEEE TASLP]

True full-duplex acoustic echo cancellation.

Blind Source Separation and Dereverberation

Code to train a custom time-domain autoencoder to dereverb audio

SASP project: FDN reverb & cepstrum-based dereverb.

No description provided.

haoheliu/voicefixerのONNXエクスポート/推論サンプル

SOTA Open-Source Speech Enhancement R&D

Demo of the paper "Robust real-time bandwidth extension for headsets with a microphone conversion target"

🗣️ Enhance communication efficiency with Speech Repo, a browser extension for Chrome and Edge that centralizes your talking points for smoother interactions.