Skip to content

(Under construct) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

License

Notifications You must be signed in to change notification settings

cookcodes/PercepNet-Pytorch

 
 

Repository files navigation

PercepNet(Under construct)

Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

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
  • Data Creater(c++) for pytorch
  • DNNModel pytorch
  • DNNModel c++ implementation
  • Postfiltering

SampleData

clean speech - VCTK 48k wav https://datashare.is.ed.ac.uk/handle/10283/2791 (clean_train_set) noise data - DEMAND 48k wav https://zenodo.org/record/1227121#__sid=js0 (*.48k.zip)

Reference

https://github.com/wil-j-wil/py_bank

https://github.com/dgaspari/pyrapt

https://github.com/xiph/rnnoise

About

(Under construct) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 34.2%
  • Python 33.3%
  • C 28.1%
  • Jupyter Notebook 2.3%
  • Shell 1.8%
  • CMake 0.3%