dereverberation 开源项目推荐（31 个）

haoheliu /voicefixer

General Speech Restoration

fgnt /nara_wpe

Different implementations of "Weighted Prediction Error" for speech dereverberation

Audio-WestlakeU /NBSS

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

adobe-research /MetaAF

Control adaptive filters with neural networks.

sekiguchi92 /SoundSourceSeparation

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

helianvine /fdndlp

A speech dereverberation algorithm, also called wpe

nay0648 /unified2021

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

DiegoLeon96 /Neural-Speech-Dereverberation

Machine and Deep Learning models for speech dereverberation

cyrta /awesome-speech-enhancement

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

rapidly-labs /rapidly-sdk

Realtime audio separation running fully on-device across iOS, macOS, Android, Linux and Windows

shamim-hussain /speech_dereverbaration_using_lp_residual

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

Audio-WestlakeU /RVAE-EM

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

echocatzh /py-aec-unified2021

该项目在 GitHub 上没有填写描述

Audio-WestlakeU /VINP

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

realclearsense /Real_AEC_Windows

True full-duplex acoustic echo cancellation.

rrbluke /BSSD

Blind Source Separation and Dereverberation

ksasso1028 /audio-reverb-removal

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

romarayt /make-normal-voice

Make Normal Voice: an Agent Skill that turns any speech recording into a clean, close-mic podcast-style voice track, locally, with measured verification (Sidon restoration, compressor-free mix, 1 ms sync).

FredReeva /SASP-FDN-Dereverb

SASP project: FDN reverb & cepstrum-based dereverb.

Haibit /cdr-dereverb

Coherence-based Dereverberation for Speech Enhancement