Coder Social home page Coder Social logo

classify_folksongs's Introduction

Classifying Folksongs Project

Overview

woop woop This project is an investigation whether or not extracted featuers of melodies can be used to train some sort of ML classifier. The idea is to explore a bit with it and then write it up into a small paper for the Journal of New Music Research. The big goals of the project are

  • Get small publication in JNMR
  • Learn about various ML classification methods

Tasks

Current

  • Redownload Essen Collection with All Countries
  • Rerun Feature Extraction Script
  • Get American Folk Songs from Kodaly
  • Get Meertens Dutsch Folk Song (Peter Von Kranenberg?)
  • Convert RS200 Melody to Krn

Literature Review

Methods

Data

  • Get Essen Collection Features 6210
  • Get American Features http://kodaly.hnu.edu/collection.cfm 522
  • Chinese Features?
  • Write R Script to Add in More Humdrum Metadata (Like German Region)
  • Get Complete Densmore
  • Convert Densmore Collection

Analysis

  • Create Cleaning Script of Extracted Features
  • Write rationale why ML method of choice will be used in accordance with Hypotheses
  • Create charts based on classification findings

Discussion

  • Wait until Introduction and Methods have been written.

Project Log

  1. Project Started: Fri Dec 22 11:27:18 2017
    • Wrote Markdown File Outline
    • Started Project Files, Git, Ball rolling
  2. Return after break Wed Jan 10 18:04:57 2017
    • Read Toiviainen and Eerola 2001 (Very basic attempt at neural net to show similarity across 6 features)
    • Spent almost entire day waiting for loops and fixing problems with batch convert of essen AND asia features
    • Converted densmore collection after dinner
  3. Added in ESAC region information Thu Jan 11 13:04:30
    • Added R code to add in region information for essen
    • Also created columns for subsetting of Densmore Collections
  4. Emailed Kodaly Center again, set up outline for paper
  5. Started Exploratory Script Friday Jan 19 11:45:30
    • Get full Essen from DS
    • Talk ML techniques w DS meeting, NN, KNN, Decision Tree
    • Recursive
  6. Convert Densmore Complete
    • Still need to move files around

classify_folksongs's People

Contributors

davidjohnbaker1 avatar shanahdt avatar

Watchers

 avatar  avatar  avatar

Forkers

shanahdt

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.