PercepNet
Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech described in https://arxiv.org/abs/2008.04259
https://www.researchgate.net/publication/343568932_A_Perceptually-Motivated_Approach_for_Low-Complexity_Real-Time_Enhancement_of_Fullband_Speech
Todo
pitch estimation
Comb filter
ERBBand c++ implementation
Feature(r,g,pitch,corr) Generator(c++) for pytorch
DNNModel pytorch
DNNModel c++ implementation
Pretrained model
Postfiltering (done by @TeaPoly )
Requirements
CMake
Sox
Python>=3.6
Pytorch
Prepare sampledata
download and sythesize data DNS-Challenge 2020 Dataset before excute utils/run.sh for training.
bash 复制
git clone -b interspeech2020/master https://github.com/microsoft/DNS-Challenge.git
Follow the Usage instruction in DNS Challenge repo(https://github.com/microsoft/DNS-Challenge ) at interspeech2020/master branch. please modify save directories at DNS-Challenge/noisyspeech_synthesizer.cfg sampledata/speech and sampledata/noise each.
Build & Training
This repository is tested on Ubuntu 20.04(WSL2)
setup CMake build environments
bash 复制
sudo apt-get install cmake
make binary directory & build
bash 复制
mkdir bin && cd bin
cmake ..
make -j
cd ..
feature generation for training with sampleData
复制
bin/src/percepNet sampledata/speech/speech.pcm sampledata/noise/noise.pcm 4000 test.output
Convert output binary to h5
复制
python3 utils/bin2h5.py test.output training.h5
Training
run utils/run.sh
Dump weight from pytorch to c++ header
复制
python3 dump_percepnet.py model.pt
Inference
bash 复制
cd bin
cmake ..
make -j1
cd ..
bin/src/percepNet_run test_input.pcm percepnet_output.pcmAcknowledgements
@jasdasdf , @sTarAnna , @cookcodes , @xyx361100238 , @zhangyutf , @TeaPoly , @rameshkunasi , @OscarLiau , @YangangCao , Jaeyoung Yang
IIP Lab. Sogang Univ
Reference
https://github.com/wil-j-wil/py_bank
https://github.com/dgaspari/pyrapt
https://github.com/xiph/rnnoise
https://github.com/mozilla/LPCNet