Music Information Retrieval

John Ashley Burgoyne, Ichiro Fujinaga, J Stephen Downie

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Music information retrieval (MIR) is "a multidisciplinary research endeavor that strives to develop innovative content-based searching schemes, novel interfaces, and evolving networked delivery mechanisms in an effort to make the world's vast store of music accessible to all." MIR was born from computational musicology in the 1960s and has since grown to have links with music cognition and audio engineering, a dedicated annual conference (ISMIR) and an annual evaluation campaign (MIREX). MIR combines machine learning with expert human knowledge to use digital music data - images of music scores, "symbolic" data such as MIDI files, audio, and metadata about musical items - for information retrieval, classification and estimation, or sequence labeling. This chapter gives a brief history of MIR, introduces classical MIR tasks from optical music recognition to music recommendation systems, and outlines some of the key questions and directions for future developments in MIR.

Original languageEnglish (US)
Title of host publicationA New Companion to Digital Humanities
PublisherWiley Blackwell
Pages213-228
Number of pages16
ISBN (Electronic)9781118680605
ISBN (Print)9781118680599
DOIs
StatePublished - Nov 30 2015

Fingerprint

Music Information Retrieval
Music
File
1960s
Labeling
Metadata
Music Cognition
Multidisciplinary Research
Optical
Musicology
Human Knowledge
Evaluation
History
Information Retrieval
Annual Conference
Computational
Machine Learning
Classical music

Keywords

  • Audio engineering
  • Classification
  • Computational musicology
  • Evaluation
  • ISMIR
  • MIREX
  • Machine learning
  • Music cognition
  • Music information retrieval (MIR)
  • Sequence labeling

ASJC Scopus subject areas

  • Arts and Humanities(all)

Cite this

Burgoyne, J. A., Fujinaga, I., & Downie, J. S. (2015). Music Information Retrieval. In A New Companion to Digital Humanities (pp. 213-228). Wiley Blackwell. https://doi.org/10.1002/9781118680605.ch15

Music Information Retrieval. / Burgoyne, John Ashley; Fujinaga, Ichiro; Downie, J Stephen.

A New Companion to Digital Humanities. Wiley Blackwell, 2015. p. 213-228.

Research output: Chapter in Book/Report/Conference proceedingChapter

Burgoyne, JA, Fujinaga, I & Downie, JS 2015, Music Information Retrieval. in A New Companion to Digital Humanities. Wiley Blackwell, pp. 213-228. https://doi.org/10.1002/9781118680605.ch15
Burgoyne JA, Fujinaga I, Downie JS. Music Information Retrieval. In A New Companion to Digital Humanities. Wiley Blackwell. 2015. p. 213-228 https://doi.org/10.1002/9781118680605.ch15
Burgoyne, John Ashley ; Fujinaga, Ichiro ; Downie, J Stephen. / Music Information Retrieval. A New Companion to Digital Humanities. Wiley Blackwell, 2015. pp. 213-228
@inbook{93b7535272b242ae83e6bbd07bfb9fb5,
title = "Music Information Retrieval",
abstract = "Music information retrieval (MIR) is {"}a multidisciplinary research endeavor that strives to develop innovative content-based searching schemes, novel interfaces, and evolving networked delivery mechanisms in an effort to make the world's vast store of music accessible to all.{"} MIR was born from computational musicology in the 1960s and has since grown to have links with music cognition and audio engineering, a dedicated annual conference (ISMIR) and an annual evaluation campaign (MIREX). MIR combines machine learning with expert human knowledge to use digital music data - images of music scores, {"}symbolic{"} data such as MIDI files, audio, and metadata about musical items - for information retrieval, classification and estimation, or sequence labeling. This chapter gives a brief history of MIR, introduces classical MIR tasks from optical music recognition to music recommendation systems, and outlines some of the key questions and directions for future developments in MIR.",
keywords = "Audio engineering, Classification, Computational musicology, Evaluation, ISMIR, MIREX, Machine learning, Music cognition, Music information retrieval (MIR), Sequence labeling",
author = "Burgoyne, {John Ashley} and Ichiro Fujinaga and Downie, {J Stephen}",
year = "2015",
month = "11",
day = "30",
doi = "10.1002/9781118680605.ch15",
language = "English (US)",
isbn = "9781118680599",
pages = "213--228",
booktitle = "A New Companion to Digital Humanities",
publisher = "Wiley Blackwell",
address = "Japan",

}

TY - CHAP

T1 - Music Information Retrieval

AU - Burgoyne, John Ashley

AU - Fujinaga, Ichiro

AU - Downie, J Stephen

PY - 2015/11/30

Y1 - 2015/11/30

N2 - Music information retrieval (MIR) is "a multidisciplinary research endeavor that strives to develop innovative content-based searching schemes, novel interfaces, and evolving networked delivery mechanisms in an effort to make the world's vast store of music accessible to all." MIR was born from computational musicology in the 1960s and has since grown to have links with music cognition and audio engineering, a dedicated annual conference (ISMIR) and an annual evaluation campaign (MIREX). MIR combines machine learning with expert human knowledge to use digital music data - images of music scores, "symbolic" data such as MIDI files, audio, and metadata about musical items - for information retrieval, classification and estimation, or sequence labeling. This chapter gives a brief history of MIR, introduces classical MIR tasks from optical music recognition to music recommendation systems, and outlines some of the key questions and directions for future developments in MIR.

AB - Music information retrieval (MIR) is "a multidisciplinary research endeavor that strives to develop innovative content-based searching schemes, novel interfaces, and evolving networked delivery mechanisms in an effort to make the world's vast store of music accessible to all." MIR was born from computational musicology in the 1960s and has since grown to have links with music cognition and audio engineering, a dedicated annual conference (ISMIR) and an annual evaluation campaign (MIREX). MIR combines machine learning with expert human knowledge to use digital music data - images of music scores, "symbolic" data such as MIDI files, audio, and metadata about musical items - for information retrieval, classification and estimation, or sequence labeling. This chapter gives a brief history of MIR, introduces classical MIR tasks from optical music recognition to music recommendation systems, and outlines some of the key questions and directions for future developments in MIR.

KW - Audio engineering

KW - Classification

KW - Computational musicology

KW - Evaluation

KW - ISMIR

KW - MIREX

KW - Machine learning

KW - Music cognition

KW - Music information retrieval (MIR)

KW - Sequence labeling

UR - http://www.scopus.com/inward/record.url?scp=84982231254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84982231254&partnerID=8YFLogxK

U2 - 10.1002/9781118680605.ch15

DO - 10.1002/9781118680605.ch15

M3 - Chapter

AN - SCOPUS:84982231254

SN - 9781118680599

SP - 213

EP - 228

BT - A New Companion to Digital Humanities

PB - Wiley Blackwell

ER -