Skip to content

Latest commit

 

History

History
43 lines (38 loc) · 1.61 KB

README.md

File metadata and controls

43 lines (38 loc) · 1.61 KB
tags: MIR, NTHU, music-information-retrieval, tempo estimation

Homework 2 for Music Information Retrieval

Environment

  • Ubuntu 18.04.1 #5.3.0-46-generic
  • Python 3.6.9 (using NeoVim v0.3.8)
  • Extra packages: see requirements.txt

Dataset

  1. Download the .wav files.
  2. Download the tempo and beat annotations.
  3. Modified the DB variables to where you decomposition the data.

Prerequisite

In this repo, the pipenv python package was used to manage this project's python package. pipenv provides a handy way to deploy projects. To use pipenv, first, you need to install it.

$ sudo python3 -m pip install --user pipenv

Once you have done the installation, run below code to install the packages that you need in this HW:

$ pipenv shell 
$ pipenv sync

Usages

The source JCM files are .mp3 format. The intuitive way to implement the MIR is to utilize .wav files. Here, we also provided the converting program: mp3Towav.sh. To convet from .mp3 to .wav, you first need to install ffmepg tool.

$ sudo apt-get install ffmpeg

Second, you need to modify the target file variable in the mp3Towav.sh file.

JCMFILES=./JCS/JCS_audio

Discussions of HW

Task1-Task2 in this HW was been done. The discussion and the results were showed on here. Enjoy it!