Four Challenges for Music Information Retrieval Researchers

Bob L. Sturm, Nick Collins

Research output: Contribution to conference without publisher/journalConference abstract for conferenceResearchpeer-review

Abstract

Exemplified in the substantial amount of published research in music genre recognition, mood recognition and autotagging, content-based music information retrieval (MIR) advances an "engineering approach'': build a system producing the most "correct'' answers in datasets appearing throughout the literature. However, it has been clearly shown that much of this research is deficient in: formally and explicitly defining problems and use cases; identifying and testing underlying assumptions;
and using evaluation with the validity to address relevant hypotheses. This means that a system so engineered might not even be considering the through it answers "correctly''. It could thus be worthless for addressing real-world problems that must consider (e.g., music description). To emphasise the critical points above, and encourage a new approaches to research that address real-world problems,
we present four challenges for MIR researchers.
Original languageEnglish
Publication date2015
Publication statusPublished - 2015
EventDigital Music Research Network 9 - Queen Mary University of London, London, United Kingdom
Duration: 16 Dec 201416 Dec 2014

Workshop

WorkshopDigital Music Research Network 9
LocationQueen Mary University of London
CountryUnited Kingdom
CityLondon
Period16/12/201416/12/2014

Fingerprint

Information retrieval
Testing

Cite this

Sturm, B. L., & Collins, N. (2015). Four Challenges for Music Information Retrieval Researchers. Abstract from Digital Music Research Network 9, London, United Kingdom.
Sturm, Bob L. ; Collins, Nick. / Four Challenges for Music Information Retrieval Researchers. Abstract from Digital Music Research Network 9, London, United Kingdom.
@conference{50328d9de0a54448ba79adaa1b0ecd1a,
title = "Four Challenges for Music Information Retrieval Researchers",
abstract = "Exemplified in the substantial amount of published research in music genre recognition, mood recognition and autotagging, content-based music information retrieval (MIR) advances an {"}engineering approach'': build a system producing the most {"}correct'' answers in datasets appearing throughout the literature. However, it has been clearly shown that much of this research is deficient in: formally and explicitly defining problems and use cases; identifying and testing underlying assumptions;and using evaluation with the validity to address relevant hypotheses. This means that a system so engineered might not even be considering the through it answers {"}correctly''. It could thus be worthless for addressing real-world problems that must consider (e.g., music description). To emphasise the critical points above, and encourage a new approaches to research that address real-world problems,we present four challenges for MIR researchers.",
author = "Sturm, {Bob L.} and Nick Collins",
year = "2015",
language = "English",
note = "Digital Music Research Network 9 ; Conference date: 16-12-2014 Through 16-12-2014",

}

Sturm, BL & Collins, N 2015, 'Four Challenges for Music Information Retrieval Researchers' Digital Music Research Network 9, London, United Kingdom, 16/12/2014 - 16/12/2014, .

Four Challenges for Music Information Retrieval Researchers. / Sturm, Bob L.; Collins, Nick.

2015. Abstract from Digital Music Research Network 9, London, United Kingdom.

Research output: Contribution to conference without publisher/journalConference abstract for conferenceResearchpeer-review

TY - ABST

T1 - Four Challenges for Music Information Retrieval Researchers

AU - Sturm, Bob L.

AU - Collins, Nick

PY - 2015

Y1 - 2015

N2 - Exemplified in the substantial amount of published research in music genre recognition, mood recognition and autotagging, content-based music information retrieval (MIR) advances an "engineering approach'': build a system producing the most "correct'' answers in datasets appearing throughout the literature. However, it has been clearly shown that much of this research is deficient in: formally and explicitly defining problems and use cases; identifying and testing underlying assumptions;and using evaluation with the validity to address relevant hypotheses. This means that a system so engineered might not even be considering the through it answers "correctly''. It could thus be worthless for addressing real-world problems that must consider (e.g., music description). To emphasise the critical points above, and encourage a new approaches to research that address real-world problems,we present four challenges for MIR researchers.

AB - Exemplified in the substantial amount of published research in music genre recognition, mood recognition and autotagging, content-based music information retrieval (MIR) advances an "engineering approach'': build a system producing the most "correct'' answers in datasets appearing throughout the literature. However, it has been clearly shown that much of this research is deficient in: formally and explicitly defining problems and use cases; identifying and testing underlying assumptions;and using evaluation with the validity to address relevant hypotheses. This means that a system so engineered might not even be considering the through it answers "correctly''. It could thus be worthless for addressing real-world problems that must consider (e.g., music description). To emphasise the critical points above, and encourage a new approaches to research that address real-world problems,we present four challenges for MIR researchers.

M3 - Conference abstract for conference

ER -

Sturm BL, Collins N. Four Challenges for Music Information Retrieval Researchers. 2015. Abstract from Digital Music Research Network 9, London, United Kingdom.