Home

About

This is the course website for 10420CS 573100 “Music Information Retrieval", National Tsing Hua University, Taiwan

Time & Location

Thursday 9:10-12:00, Feb 18 – June 16, 2016
DELTA (台達館) Room 103, National Tsing Hua University

Lecturers

  • We have two lecturers for this course
    • Yi-Hsuan Yang, Ph.D., Academia Sinica (HTML, MAIL)
    • Li Su, Ph.D., Academia Sinica  (HTML, MAIL)
  • Office hour: Friday 9-11am, or by appointment
  • Office: 資電館 645室

TA

  • Jeffrey Huang (MAIL)
  • Office hour: Thursday 1-3pm
  • Office: 資電館719室

Course Objective

To introduce the fundamentals of music information retrieval techniques.  Good for those who are interested in digital signal processing, machine learning, information retrieval, and data science.  This course is in particular for those who love music!

We will emphasize implementation in this course.  The ability to program in either Matlab or python is a prerequisite.  This course will have four programming assignments, and one final project.

Textbook

Fundamentals of Music Processing: Audio, Analysis, Algorithms, Applications (HTML)

Grading

Participation 10%
Assignments 60%
Final project 30%
(We reserve the right to adjust the weights)

Course Outline

  • W1 (2/18): Intro (slides, supp)
  • W2 (2/25): Short time Fourier Transform (slides, supp)
  • W3 (3/03): Timbre (slides, supp) 
  • W4 (3/10): Classification (slides)  
  • W5 (3/17): Pitch & chord 1/3 (slides)
  • W6 (3/24): Synchronization (slides)
  • W7 (3/31): Pitch & chord 2/3 (slides) 
  • W8 (4/07): Pitch & chord 3/3 (slides)
  • W9 (4/14): Separation 1/3 (slides)
  • W10 (4/21): Separation 2/3 (slides)
  • W11 (4/28): Separation 3/3 (slides)
  • W12 (5/05): Beat, tempo & rhythm 1/2 
  • W13 (5/12): Beat, tempo & rhythm 2/2 (slides)
  • W14 (5/19): Structure analysis (slides) 
  • W15 (5/26): Tagging & recommendation (slides, link_1, link_2, link_3, link_4, link_5, link_6last update: 0524
  • W16 (6/02): Research at MAClab, Academia Sinica (slideslast update: 0530
  • W18 (6/16): Final project

Final Project

Goal: Invite you to contribute to this field

For a team of 3 or less

Possible topics (to be updated later)

  • Melodic transcription for a specific genre of music: Piano quintet, string quartet, violin sonata, voice duet, choir, wind quintet, etc
  • Real-time score following
  • Cross-cultural MIR Taiwanese Pop songs, folk songs, aboriginal music, etc
  • Or on your own

Project pitch (presentation of your ideas): W10
Deadline for team up: W12

Evaluation criteria for the oral presentation:

  • Maturity of the project (how complete/mature the project is done)
  • Difficulty (how challenging the proposed topic is)
  • Presentation
  • Novelty (how novel/interesting the idea is)
  • Applicability (how the presented work can be applied in real life applications)

Each team has 5 mins for the oral presentation on June 16.

Project report deadline: June 23 (Thursday) 23:59pm

(You are encouraged to consider submitting something to the domestic track of the TAAI conference, which is going to take place in NTHU later this year.  The deadline for paper submission is July 15.  See http://www.cs.nthu.edu.tw/~taai2016/keydates.html)

Resources

Dan Ellis @ Columbia (moved to Google)
https://www.ee.columbia.edu/~dpwe/

Meinard Meuller @ Universität Erlangen-Nürnberg
https://www.audiolabs-erlangen.de/fau/professor/mueller/teaching

Juan Bello @ NYU
http://www.nyu.edu/classes/bello/Teaching.html

CCRMA summer school @ Stanford
https://ccrma.stanford.edu/workshops/music-information-retrieval-mir-2015

Xavier Serra @ UPF, Spain
https://zh-tw.coursera.org/course/audio

Roger Jang @ NTU
http://mirlab.org/jang/

MIREX
http://www.music-ir.org/mirex/wiki/MIREX_HOME