Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 

Analysis of Master's Thesis Results

The topic of my Master's thesis is score-informed source separation of choral music. This repository contains code used to analyze experiment results and generate figures for the thesis. The code is written as Jupyter notebooks and saved as Python files. To open the notebooks, install Jupyter Notebook (or Jupyter Lab) and Jupytext.

  • nmf.py: figures for section 2.1 (Audio Source Separation).
  • deep_learning.py: figures for section 2.2 (Deep Learning).
  • nmf_experiments.py: analyses for chapter 4 (Score-Informed NMF for Choral Music).
  • analysis_wave-u-net.py: analyses for chapter 5 (Wave-U-Net for Choral Music).
  • analysis_wave-u-net_score_informed.py: analyses for chapter 6 (Score-Informed Wave-U-Net).
  • sdr_analysis.py: analyses for section 6.3.8 (Limitations of SDR).
  • utils.py: shared utilities.

The following repositories were also created as part of this thesis:

About

Analysis of thesis experiment results

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages