Pinned Repositories
bmf
Cross-platform, customizable multimedia/video processing framework. With strong GPU acceleration, heterogeneous design, multi-language support, easy to use, multi-framework compatible and high performance, the framework is ideal for transcoding, AI inference, algorithm integration, live video streaming, and more.
DeepFilterNet
Noise supression using deep filtering
DNS-Challenge
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
DPCRN_DNS3
Implementation of paper "DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement"
DPCRN_DNS3_Results
Results of the blind test set of the 3rd Deep Noise Suppression Challenge
GMM_VAD
Le-Xiaohuai-speech
Config files for my GitHub profile.
SKIP-DPCRN
SKIP-DPCRN-samples
VAE_NMF
A semi-supervised single channel speech enhancement method using Variational Autoencoder and Non-negative Matrix Factorization
Le-Xiaohuai-speech's Repositories
Le-Xiaohuai-speech/DPCRN_DNS3
Implementation of paper "DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement"
Le-Xiaohuai-speech/SKIP-DPCRN
Le-Xiaohuai-speech/GMM_VAD
Le-Xiaohuai-speech/DPCRN_DNS3_Results
Results of the blind test set of the 3rd Deep Noise Suppression Challenge
Le-Xiaohuai-speech/VAE_NMF
A semi-supervised single channel speech enhancement method using Variational Autoencoder and Non-negative Matrix Factorization
Le-Xiaohuai-speech/Le-Xiaohuai-speech
Config files for my GitHub profile.
Le-Xiaohuai-speech/SKIP-DPCRN-samples
Le-Xiaohuai-speech/bmf
Cross-platform, customizable multimedia/video processing framework. With strong GPU acceleration, heterogeneous design, multi-language support, easy to use, multi-framework compatible and high performance, the framework is ideal for transcoding, AI inference, algorithm integration, live video streaming, and more.
Le-Xiaohuai-speech/DeepFilterNet
Noise supression using deep filtering
Le-Xiaohuai-speech/DNS-Challenge
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
Le-Xiaohuai-speech/PercepNet
(Work In Progress) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech
Le-Xiaohuai-speech/TensorflowASR
集成了Tensorflow 2版本的端到端语音识别模型，并且RTF(实时率)在0.1左右/Mandarin State-of-the-art Automatic Speech Recognition in Tensorflow 2
Le-Xiaohuai-speech/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
Le-Xiaohuai-speech/WenzheLiu-Speech.github.io