sx1105092 Goto Github PK

aec_deepmodel

基于深度学习的声学回声消除基线代码

andyfeng

hahha

asr_theory

语音识别理论，论文和PPT

athena-signal

beamforming-for-speech-enhancement

simple delaysum, MVDR and CGMM-MVDR

bf-design-with-dl

Beamforming design with deep learning.

cgmm-mvdr

Implementation of the CGMM-MVDR beamforming (for python version please refer to https://github.com/funcwj/setk)

deepfilternet

Noise supression using deep filtering

denoising_dihard18

dnn-for-speech-enhancement

DNN-for-speech-enhancement

dnn-speech-enhancement-demo-tool

Universal Deep neural network based speech enhancement demo and tools, well pre-trained DNN model

dns-challenge

This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.

dtln

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

dtln-aec

This Repostory contains the pretrained DTLN-aec model for real-time acoustic echo cancellation.

fdndlp

A speech dereverberation algorithm, also called wpe

logmmse

LogMMSE speech enhancement/noise reduction

magenta

Magenta: Music and Art Generation with Machine Intelligence

mosquitto

Eclipse Mosquitto - An open source MQTT broker

nara_wpe

Different implementations of "Weighted Prediction Error" for speech dereverberation

nkf-aec

Acoustic Echo Cancellation with Nerual Kalman Filtering

nn_mask

multichannel linear filters based on mask estimation neural networks for CHiME4

nres

Neural Residual Echo Suppressor

pagan

PAGAN: a phase-adapted GAN for speech enhancement

pesq

PESQ (Perceptual Evaluation of Speech Quality) Wrapper for Python Users (narrow band and wide band)

pyaec

simple and efficient python implemention of a series of adaptive filters. including time domain adaptive filters(lms、nlms、rls、ap、kalman)、nonlinear adaptive filters(volterra filter、functional link adaptive filters)、frequency domain adaptive filters(frequency domain adaptive filter、frequency domain kalman filter) for acoustic echo cancellation.

pykan

Kolmogorov Arnold Networks

pyrirgen

pyrir pyrirgen-add source directivity. Basd on the RIR source code from《Room Impulse Response Generator》, we modify it and add the new function of source directivity. azimuth ∈ (pi, pi], 0 represents the positive X axis direction; elevation ∈ [-pi/2, pi/2], 0 represents the horizontal direction. Make sure you installed NumPy and Cython (pip instal

rir-generator

Generating room impulse responses

sednn

deep learning based speech enhancement using keras or pytorch, make it easy to use

segan

Speech Enhancement Generative Adversarial Network in TensorFlow