Heming Wang's repositories
A-Convolutional-Recurrent-Neural-Network-for-Real-Time-Speech-Enhancement
Implement A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement by PyTorch.
NS-Outpainting
Very Long Natural Scenery Image Prediction by Outpainting, ICCV2019, TensorFlow
kaldi
This is the official location of the Kaldi project.
Conv-TasNet
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
LSTM_PIT_Speech_Separation
Multi-talker Speech Separation with LSTM/BLSTM by Permutation Invariant Training method.
python_speech_features
This library provides common speech features for ASR including MFCCs and filterbank energies.
music-source-separation
Separating singing voice from music based on deep neural networks in Tensorflow
Bayesian-BSS
Bayesian Blind Source Separation
cs350-till-a2a
THIS IS ASSIGNMENT ANSWER FOR UWATERLOO CS350 Fall 2017 till 2a
luoo_stats
Data fetched from luoo.net
FetchText_UWbulletin
Fetch brief news from UW bulletin
friture
Real-time audio visualizations (spectrum, spectrogram, etc.)
Heming-Audio
Audio programs
Python_Scientific_Computing
Python Scientific Computing - Qt, Realtime wave, Signal Analysis
Pat-DataStructure
Data structure exercises written in c++
Fake_Zhihu
An app designed to read information from Zhihu rapidly (Can be used as rss reader with tiny revision)
SunShine
Practice app
DataStructure-C
Data Structure C Exercises
DragonGoApp
Android app to play the game of go with the DGS and OGS servers
BallonGame
A small game written in c# with XNA framework