Evaluating hierarchical structure in music annotations

Brian McFee, Oriol Nieto, Morwaread Farbood, Juan Bello

Research output: Contribution to journalArticle

Abstract

Music exhibits structure at multiple scales, ranging from motifs to large-scale functional components. When inferring the structure of a piece, different listeners may attend to different temporal scales, which can result in disagreements when they describe the same piece. In the field of music informatics research (MIR), it is common to use corpora annotated with structural boundaries at different levels. By quantifying disagreements between multiple annotators, previous research has yielded several insights relevant to the study of music cognition. First, annotators tend to agree when structural boundaries are ambiguous. Second, this ambiguity seems to depend on musical features, time scale, and genre. Furthermore, it is possible to tune current annotation evaluation metrics to better align with these perceptual differences. However, previous work has not directly analyzed the effects of hierarchical structure because the existing methods for comparing structural annotations are designed for "flat" descriptions, and do not readily generalize to hierarchical annotations. In this paper, we extend and generalize previous work on the evaluation of hierarchical descriptions of musical structure. We derive an evaluation metric which can compare hierarchical annotations holistically across multiple levels. sing this metric, we investigate inter-annotator agreement on the multilevel annotations of two different music corpora, investigate the influence of acoustic properties on hierarchical annotations, and evaluate existing hierarchical segmentation algorithms against the distribution of inter-annotator agreement.

Original languageEnglish (US)
Article number1337
JournalFrontiers in Psychology
Volume8
Issue numberAUG
DOIs
StatePublished - Aug 3 2017

Fingerprint

Music
Informatics
Research
Acoustics
Cognition

Keywords

  • Evaluation
  • Hierarchy
  • Inter-annotator agreement
  • Music structure

ASJC Scopus subject areas

  • Psychology(all)

Cite this

Evaluating hierarchical structure in music annotations. / McFee, Brian; Nieto, Oriol; Farbood, Morwaread; Bello, Juan.

In: Frontiers in Psychology, Vol. 8, No. AUG, 1337, 03.08.2017.

Research output: Contribution to journalArticle

@article{640a3a85808947a788843367abfade63,
title = "Evaluating hierarchical structure in music annotations",
abstract = "Music exhibits structure at multiple scales, ranging from motifs to large-scale functional components. When inferring the structure of a piece, different listeners may attend to different temporal scales, which can result in disagreements when they describe the same piece. In the field of music informatics research (MIR), it is common to use corpora annotated with structural boundaries at different levels. By quantifying disagreements between multiple annotators, previous research has yielded several insights relevant to the study of music cognition. First, annotators tend to agree when structural boundaries are ambiguous. Second, this ambiguity seems to depend on musical features, time scale, and genre. Furthermore, it is possible to tune current annotation evaluation metrics to better align with these perceptual differences. However, previous work has not directly analyzed the effects of hierarchical structure because the existing methods for comparing structural annotations are designed for {"}flat{"} descriptions, and do not readily generalize to hierarchical annotations. In this paper, we extend and generalize previous work on the evaluation of hierarchical descriptions of musical structure. We derive an evaluation metric which can compare hierarchical annotations holistically across multiple levels. sing this metric, we investigate inter-annotator agreement on the multilevel annotations of two different music corpora, investigate the influence of acoustic properties on hierarchical annotations, and evaluate existing hierarchical segmentation algorithms against the distribution of inter-annotator agreement.",
keywords = "Evaluation, Hierarchy, Inter-annotator agreement, Music structure",
author = "Brian McFee and Oriol Nieto and Morwaread Farbood and Juan Bello",
year = "2017",
month = "8",
day = "3",
doi = "10.3389/fpsyg.2017.01337",
language = "English (US)",
volume = "8",
journal = "Frontiers in Psychology",
issn = "1664-1078",
publisher = "Frontiers Media S. A.",
number = "AUG",

}

TY - JOUR

T1 - Evaluating hierarchical structure in music annotations

AU - McFee, Brian

AU - Nieto, Oriol

AU - Farbood, Morwaread

AU - Bello, Juan

PY - 2017/8/3

Y1 - 2017/8/3

N2 - Music exhibits structure at multiple scales, ranging from motifs to large-scale functional components. When inferring the structure of a piece, different listeners may attend to different temporal scales, which can result in disagreements when they describe the same piece. In the field of music informatics research (MIR), it is common to use corpora annotated with structural boundaries at different levels. By quantifying disagreements between multiple annotators, previous research has yielded several insights relevant to the study of music cognition. First, annotators tend to agree when structural boundaries are ambiguous. Second, this ambiguity seems to depend on musical features, time scale, and genre. Furthermore, it is possible to tune current annotation evaluation metrics to better align with these perceptual differences. However, previous work has not directly analyzed the effects of hierarchical structure because the existing methods for comparing structural annotations are designed for "flat" descriptions, and do not readily generalize to hierarchical annotations. In this paper, we extend and generalize previous work on the evaluation of hierarchical descriptions of musical structure. We derive an evaluation metric which can compare hierarchical annotations holistically across multiple levels. sing this metric, we investigate inter-annotator agreement on the multilevel annotations of two different music corpora, investigate the influence of acoustic properties on hierarchical annotations, and evaluate existing hierarchical segmentation algorithms against the distribution of inter-annotator agreement.

AB - Music exhibits structure at multiple scales, ranging from motifs to large-scale functional components. When inferring the structure of a piece, different listeners may attend to different temporal scales, which can result in disagreements when they describe the same piece. In the field of music informatics research (MIR), it is common to use corpora annotated with structural boundaries at different levels. By quantifying disagreements between multiple annotators, previous research has yielded several insights relevant to the study of music cognition. First, annotators tend to agree when structural boundaries are ambiguous. Second, this ambiguity seems to depend on musical features, time scale, and genre. Furthermore, it is possible to tune current annotation evaluation metrics to better align with these perceptual differences. However, previous work has not directly analyzed the effects of hierarchical structure because the existing methods for comparing structural annotations are designed for "flat" descriptions, and do not readily generalize to hierarchical annotations. In this paper, we extend and generalize previous work on the evaluation of hierarchical descriptions of musical structure. We derive an evaluation metric which can compare hierarchical annotations holistically across multiple levels. sing this metric, we investigate inter-annotator agreement on the multilevel annotations of two different music corpora, investigate the influence of acoustic properties on hierarchical annotations, and evaluate existing hierarchical segmentation algorithms against the distribution of inter-annotator agreement.

KW - Evaluation

KW - Hierarchy

KW - Inter-annotator agreement

KW - Music structure

UR - http://www.scopus.com/inward/record.url?scp=85026843339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026843339&partnerID=8YFLogxK

U2 - 10.3389/fpsyg.2017.01337

DO - 10.3389/fpsyg.2017.01337

M3 - Article

AN - SCOPUS:85026843339

VL - 8

JO - Frontiers in Psychology

JF - Frontiers in Psychology

SN - 1664-1078

IS - AUG

M1 - 1337

ER -