- Notifications
You must be signed in to change notification settings - Fork1
A recursive Fourier transform (FT) structure that suppresses convolutional noise.
License
NotificationsYou must be signed in to change notification settings
yoyolicoris/multi-layered-cepstrum
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Source code of the paperMulti-Layered Cepstrum for Instantaneous Frequency Estimation accepted at GlobalSIP 2018.
- Numpy
- Scipy
- Torch (optional for faster performance)
- Librosa (file IO)
- Matplotlib (visualization)
- Pypianoroll (visualization)
- Donwloadbach10 dataset.
- Run with default parameters.
python bach10.py your/download/path/01-AchGottundHerr/01-AchGottundHerr.wav \ --f0_file your/download/path/01-AchGottundHerr/01-AchGottundHerr-GTF0s.mat...Time cost: 5.6769 secondsPrecision: 0.7661, Recall: 0.9170, F-score:, 0.8348
We also implement a faster version using PyTorch astorch_bach10.py, and it can run roughly 2 times faster on CPU.Add--cuda can further utilize computational resources on GPU.
About
A recursive Fourier transform (FT) structure that suppresses convolutional noise.
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Releases
No releases published
Packages0
No packages published