Discover @funcwj Open Source projects

Jian Wu (@funcwj)

funcwj

Stars
1,455
Global Rank 21,364 (Top 0.8 %)
Followers 577
Following 100
Registered over 8 years ago
Most used languages

Python
62.5 %

C++
25.0 %

MATLAB
6.3 %

Java
6.3 %
Location 🇺🇸 United States
Country Total Rank 6,687
Country Ranking

MATLAB
285

Python
1,129

C++
5,083

setk

Tools for Speech Enhancement integrated with Kaldi

conv-tasnet

A PyTorch implementation of "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" (see recipes in aps framework https://github.com/funcwj/aps)

CGMM-MVDR

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

aps

A personal toolkit for single/multi-channel speech recognition & enhancement & separation.

deep-clustering

deep clustering method for single-channel speech separation

ge2e-speaker-verification

Pytorch implementation of "Generalized End-to-End Loss for Speaker Verification"

uPIT-for-speech-separation

Speech separation with utterance-level PIT experiments

voice-filter

A unofficial Pytorch implementation of Google's VoiceFilter

cgmm-mask-estimator

Implementation of the offline method described in "Robust mvdr beamforming using time-frequency masks for online/offline asr in noise" (for python version please refer to https://github.com/funcwj/setk)

kaldi-python-io

A python IO interface for data accessing in kaldi

chime4-nn-mask

Implementation of NN based mask estimator in pytorch

pydecoder

A python wrapper for kaldi-online-decoder using Cython

portable-decoder

A simple, portable decoder

asr-utils

Some tools implemented in C++ for ASR

raspberry-pi-kws

A QbyE-KWS Demo runs on Raspberry Pi

android-kws

Source code for implementing KWS demo on android