Okrio

CRUSE

a lightweight network for monaural speech enhancement

tinyrecurrentunet

Real-Time De-noising and De-reverbing with Tiny Recurrent UNet

deepvqe

FSPEN

Subband-Beamformer

webrtc-resampler

resampler module from WebRTC

Beam-Guided-TasNet

Beam-guided TasNet

gtcrn

An official implementation of GTCRN, an ultra-lite speech enhancement model.

multichannel-audio-tools

paper_crawler

SWAN-Neural-Comb-Filter

AcoustDSP

Acoustic DSP is a Python library which aims to implement several digital signal processing algorithms regarding acoustic analysis in one place.

Bayesian-Pitch-Tracking-Using-Harmonic-model

Pitch detection and pitch tracking, voicing unvoicing detection (VAD)，基音检测

Double-talk-Detection-aided-Residual-Echo-Suppression-via-Spectrogram-Masking-and-Refinement

ego2022

JOINT EGO-NOISE SUPPRESSION AND KEYWORD SPOTTING ON SWEEPING ROBOTS

FQSE

Fully Quantized Neural Networks For Speech Enhancement

FRA-RIR

FullSubNet-plus

The official PyTorch implementation of "FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement".

Grad-W

GWA

Geometric-Wave Acoustic dataset

InpaintingNMF

This is the accompanying repository for the article Algorithms for audio inpainting based on probabilistic nonnegative matrix factorization authored by Ondřej Mokrý, Paul Magron, Thomas Oberlin and Cédric Févotte, submitted to Elsevier Signal Processing.

NeuralSpeech

NKF-AEC

Acoustic Echo Cancellation with Nerual Kalman Filtering

nnlib-hifi5

HiFi 5 NN Library

Okrio

PCS

Perceptual Contrast Stretching on Target Feature for Speech Enhancement (Accepted by INTERSPEECH 2022)

pygsound

Impulse response generation based on state-of-the-art geometric sound propagation engine.

ssspy

A Python toolkit for sound source separation.

webrtc-ns

noise suppression module from WebRTC

webrtc_AEC3