andong-li-speech Goto Github PK

3rd-dns-challenge-samples

ab_test_platform_taslp

This repository provides the subjective testing platform between baselines and proposed approach

andong-li-speech.github.io

anonymous_demo

This is the anonymous demo of the proposed speech enhancement system, which is submitted to XXX 2022.

assteroid

Audio Source Separation on steroids

bird

Big Impulse Response Dataset

ci_sdr

cost_aware_enhancement

Communication Aware Microphone Selection For Neural Speech Enhancement with Ad-hoc Microphone Arrays

cts-net

The supplemental material and samples with respect to the paper "TWO HEADS ARE BETTER THAN ONE: A TWO-STAGE APPROACH FOR MONAURAL NOISE REDUCTION IN THE COMPLEX DOMAIN" are provided (submitted to ICASSP 2021)

cts_taslp_demos

Some demos for CTS_Net in the submitted manuscript for TASLP

darcn

The implementation of "A Recursive Network with Dynamic Attention for Monaural Speech Enhancement"

dargan

implementation of Dynamic Attention Recursive GAN (DARGAN), the code will be released in the near furture.

ddaec

deepfilternet

Noise supression using deep filtering

demopage-voicefixer

Voicefixer is a speech restoration model that handles noise, reverberation, low resolution (2kHz~44.1kHz), and clipping (0.1-1.0 threshold) distortion simultaneously.

dilated

Smoothed Dilated Convolutions for Improved Dense Prediction

dns-challenge

This repo contains the scripts, models and required files for the Interspeech 2020 Deep Noise Suppression (DNS) Challenge. We are open sourcing clean speech and noise files as well. Participants of this challenge will use the scripts from this repo to create data to train their noise suppressors. They will compare their method with our baseline noise suppressor and report the results.

dns-challenge-iacaslab9.github.io

eabnet

This is the repo of the manuscript "Embedding and Beamforming: All-Neural Causal Beamformer for Multichannel Speech Enhancement", which was submitted to ICASSP2022.

eabnet-demo

fra-rir

fullsubnet-plus

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

g2net

The implementation of G2Net, the extension of GaGNet and is in submission to T-ASLP

gagnet

This repo provides the network code and the processed samples of the manuscript "Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancement", which was accepted by Elsevier Applied Acoustics.

generalized_loss_samples

Samples for "A Supervised Speech Enhancement Approach with Residual Noise Control for Voice Communication"

hilcodec

image-deraining-via-continual-learning

CVPR-2021

iunets

A fully intertible U-Net for memory efficiency in Pytorch.

jaecbf

listening-to-sound-of-silence-for-speech-denoising

[NeurIPS 2020] Official repository for the project "Listening to Sound of Silence for Speech Denoising"