gedebabin Goto Github PK

sdcm

A light-weight full-band speech enhancement model

sddnet

Coarse implement of the paper "A Simultaneous Denoising and Dereverberation Framework with Target Decoupling", On DNS-2020 dataset, the DNSMOS of first stage is 3.42 and second stage is 3.47.

separation_data_preparation

Data preparation for separation

setrain

A training code template for DNN-based speech enhancement.

sf-net

The implementation of "Optimizing Shoulder to Shoulder: A Coordinated Sub-Band Fusion Model for Real-Time Full-Band Speech Enhancement"

sgmse

Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation

sixty-years-of-frequency-domain-monaural-speech-enhancement

speech-resources

语音方向实验室/公司/资源/实习等，欢迎推荐或自荐

speechalgorithms

Speech Algorithms

spiking-fullsubnet

Official repository of Spiking-FullSubNet, the Intel N-DNS Challenge Algorithmic Track Winner.

spmamba

subband_kalman_aec

Subband kalman filter for echo cancellation

sudo_rm_rf

Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.

tdanet

An efficient speech separation method

text-to-sound-synthesis

The source code of our paper "Diffsound: discrete diffusion model for text-to-sound generation"

tfgan-plc

A Temporal-Spectral Generative Adversarial Network based End-to-end Packet Loss Concealment for Wideband Speech Transmission

tnn

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server.

torch-mfcc

A librosa STFT/Fbank/mfcc feature extration written up in PyTorch using 1D Convolutions.

torch-pesq

PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio

tse-fv

Target speaker extraction by fusing voiceprint features

tse-with-ref-selection

target speaker extraction with speaker reference selection

tse_pi

Official Code for Target Sound Extraction under Reverberant Environments with Pitch Information (Interspeech 2024)

tspnn

Two-stage progressive neural network for acoustic echo cancellation

uniaudio_1

The official source code of UniAudio

uniaudio_2

The Open Source Code of UniAudio

unified-enhance-separation

Code for paper "Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation"

vpidm

This is official repository of new SOTA diffusion models based method for speech enhancement

weights-initializer-pytorch

A module for making weights initialization easier in pytorch.