Skip to content

🎶 Musical instrument recognition in isolated notes and solo phrases by Gammatone and CNN

License

Notifications You must be signed in to change notification settings

ybhan/Musical-Instrument-Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Musical Instrument Recognition in Isolated Notes and Solo Phrases

By Yuanbo Han and Wenyu Zhang, November 2018.

Methodology

  • Gammatone Filtering

  • CNN

    CNN Architecture

Dataset

RWC Music Database: Musical Instrument Sound

Environment

  • MATLAB R2018a
  • Python 3.6
    • scipy 1.1
    • numpy 1.14
    • torch 1.0

Note that these are only tested versions, not the least requirements.

Usage

Run gammatone/main.m to perform Gammatone filtering, but please first check the dataset path in line 5 and line 8. To get a grasp of the dependent functions, see gammatone_demo.m for a simple example.

After preprocessing, run cnn/read_data.py to read .MAT files as .NPY format. Then execute CNN.pyto train the neural network. There is an instance (mat_files/XY.mat) for testing CNN.py without above steps.

About

🎶 Musical instrument recognition in isolated notes and solo phrases by Gammatone and CNN

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published