Content-Based Methods for Knowledge Discovery in Music

Juan Pablo Bello, Peter Grosche, Meinard Müller, Ron Weiss

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This chapter presents several computational approaches aimed at supporting knowledge discovery in music. Our work combines data mining, signal processing and data visualization techniques for the automatic analysis of digital music collections, with a focus on retrieving and understanding musical structure. We discuss the extraction of midlevel feature representations that convey musically meaningful information from audio signals, and show how such representations can be used to synchronize different instances of a musical work and enable new modes of music content browsing and navigation. Moreover, we utilize these representations to identify repetitive structures and representative patterns in the signal, via self-similarity analysis and matrix decomposition techniques that can be made invariant to changes of local tempo and key. We discuss how structural information can serve to highlight relationships within music collections, and explore the use of information visualization tools to characterize the patterns of similarity and dissimilarity that underpin such relationships. With the help of illustrative examples computed on a collection of recordings of Frédéric Chopin’s Mazurkas, we aim to show how these content-based methods can facilitate the development of novel modes of access, analysis and interaction with digital content that can empower the study and appreciation of music.

Original languageEnglish (US)
Title of host publicationSpringer Handbooks
PublisherSpringer
Pages823-840
Number of pages18
DOIs
StatePublished - Jan 1 2018

Publication series

NameSpringer Handbooks
ISSN (Print)2522-8692
ISSN (Electronic)2522-8706

Fingerprint

Data mining
Data visualization
Signal processing
Navigation
Visualization
Decomposition

ASJC Scopus subject areas

  • General

Cite this

Bello, J. P., Grosche, P., Müller, M., & Weiss, R. (2018). Content-Based Methods for Knowledge Discovery in Music. In Springer Handbooks (pp. 823-840). (Springer Handbooks). Springer . https://doi.org/10.1007/978-3-662-55004-5_39

Content-Based Methods for Knowledge Discovery in Music. / Bello, Juan Pablo; Grosche, Peter; Müller, Meinard; Weiss, Ron.

Springer Handbooks. Springer , 2018. p. 823-840 (Springer Handbooks).

Research output: Chapter in Book/Report/Conference proceedingChapter

Bello, JP, Grosche, P, Müller, M & Weiss, R 2018, Content-Based Methods for Knowledge Discovery in Music. in Springer Handbooks. Springer Handbooks, Springer , pp. 823-840. https://doi.org/10.1007/978-3-662-55004-5_39
Bello JP, Grosche P, Müller M, Weiss R. Content-Based Methods for Knowledge Discovery in Music. In Springer Handbooks. Springer . 2018. p. 823-840. (Springer Handbooks). https://doi.org/10.1007/978-3-662-55004-5_39
Bello, Juan Pablo ; Grosche, Peter ; Müller, Meinard ; Weiss, Ron. / Content-Based Methods for Knowledge Discovery in Music. Springer Handbooks. Springer , 2018. pp. 823-840 (Springer Handbooks).
@inbook{eb857c11c16049a3a8871567118f6903,
title = "Content-Based Methods for Knowledge Discovery in Music",
abstract = "This chapter presents several computational approaches aimed at supporting knowledge discovery in music. Our work combines data mining, signal processing and data visualization techniques for the automatic analysis of digital music collections, with a focus on retrieving and understanding musical structure. We discuss the extraction of midlevel feature representations that convey musically meaningful information from audio signals, and show how such representations can be used to synchronize different instances of a musical work and enable new modes of music content browsing and navigation. Moreover, we utilize these representations to identify repetitive structures and representative patterns in the signal, via self-similarity analysis and matrix decomposition techniques that can be made invariant to changes of local tempo and key. We discuss how structural information can serve to highlight relationships within music collections, and explore the use of information visualization tools to characterize the patterns of similarity and dissimilarity that underpin such relationships. With the help of illustrative examples computed on a collection of recordings of Fr{\'e}d{\'e}ric Chopin’s Mazurkas, we aim to show how these content-based methods can facilitate the development of novel modes of access, analysis and interaction with digital content that can empower the study and appreciation of music.",
author = "Bello, {Juan Pablo} and Peter Grosche and Meinard M{\"u}ller and Ron Weiss",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-662-55004-5_39",
language = "English (US)",
series = "Springer Handbooks",
publisher = "Springer",
pages = "823--840",
booktitle = "Springer Handbooks",

}

TY - CHAP

T1 - Content-Based Methods for Knowledge Discovery in Music

AU - Bello, Juan Pablo

AU - Grosche, Peter

AU - Müller, Meinard

AU - Weiss, Ron

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This chapter presents several computational approaches aimed at supporting knowledge discovery in music. Our work combines data mining, signal processing and data visualization techniques for the automatic analysis of digital music collections, with a focus on retrieving and understanding musical structure. We discuss the extraction of midlevel feature representations that convey musically meaningful information from audio signals, and show how such representations can be used to synchronize different instances of a musical work and enable new modes of music content browsing and navigation. Moreover, we utilize these representations to identify repetitive structures and representative patterns in the signal, via self-similarity analysis and matrix decomposition techniques that can be made invariant to changes of local tempo and key. We discuss how structural information can serve to highlight relationships within music collections, and explore the use of information visualization tools to characterize the patterns of similarity and dissimilarity that underpin such relationships. With the help of illustrative examples computed on a collection of recordings of Frédéric Chopin’s Mazurkas, we aim to show how these content-based methods can facilitate the development of novel modes of access, analysis and interaction with digital content that can empower the study and appreciation of music.

AB - This chapter presents several computational approaches aimed at supporting knowledge discovery in music. Our work combines data mining, signal processing and data visualization techniques for the automatic analysis of digital music collections, with a focus on retrieving and understanding musical structure. We discuss the extraction of midlevel feature representations that convey musically meaningful information from audio signals, and show how such representations can be used to synchronize different instances of a musical work and enable new modes of music content browsing and navigation. Moreover, we utilize these representations to identify repetitive structures and representative patterns in the signal, via self-similarity analysis and matrix decomposition techniques that can be made invariant to changes of local tempo and key. We discuss how structural information can serve to highlight relationships within music collections, and explore the use of information visualization tools to characterize the patterns of similarity and dissimilarity that underpin such relationships. With the help of illustrative examples computed on a collection of recordings of Frédéric Chopin’s Mazurkas, we aim to show how these content-based methods can facilitate the development of novel modes of access, analysis and interaction with digital content that can empower the study and appreciation of music.

UR - http://www.scopus.com/inward/record.url?scp=85075934219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075934219&partnerID=8YFLogxK

U2 - 10.1007/978-3-662-55004-5_39

DO - 10.1007/978-3-662-55004-5_39

M3 - Chapter

AN - SCOPUS:85075934219

T3 - Springer Handbooks

SP - 823

EP - 840

BT - Springer Handbooks

PB - Springer

ER -