A comparison of statistical and rule-based models for style-specific harmonization

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The process of generating chords for harmonizing a melody with the goal of mimicking an artist's style is investigated in this paper. We compared and tested three different approaches, including a rule-based model, a statistical model, and a hybrid system of the two, for such tasks. Experiments were conducted using songs from seven stylistically identifiable pop/rock bands, and the chords generated by the systems were compared to the ones in the artists' original work. Evaluations were performed on multiple aspects, including calculating the average percentage of chords that were the same and those that were related, studying the manner in which the size of the training set affects the output harmonization, and examining a system's behaviors in terms of the ability of generating unseen chords and the number of unique chords produced per song. We observed that the rule-based system performs comparably well while the result of the system with learning capability varies as the training set grows.

Original languageEnglish (US)
Title of host publicationProceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011
Pages221-226
Number of pages6
StatePublished - Dec 1 2011
Externally publishedYes
Event12th International Society for Music Information Retrieval Conference, ISMIR 2011 - Miami, FL, United States
Duration: Oct 24 2011Oct 28 2011

Other

Other12th International Society for Music Information Retrieval Conference, ISMIR 2011
CountryUnited States
CityMiami, FL
Period10/24/1110/28/11

Fingerprint

Knowledge based systems
Hybrid systems
Rocks
Experiments
Statistical Models
Chord
Harmonization
Artist
Song

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Chuan, C-H. (2011). A comparison of statistical and rule-based models for style-specific harmonization. In Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011 (pp. 221-226)

A comparison of statistical and rule-based models for style-specific harmonization. / Chuan, Ching-Hua.

Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011. 2011. p. 221-226.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chuan, C-H 2011, A comparison of statistical and rule-based models for style-specific harmonization. in Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011. pp. 221-226, 12th International Society for Music Information Retrieval Conference, ISMIR 2011, Miami, FL, United States, 10/24/11.
Chuan C-H. A comparison of statistical and rule-based models for style-specific harmonization. In Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011. 2011. p. 221-226
Chuan, Ching-Hua. / A comparison of statistical and rule-based models for style-specific harmonization. Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011. 2011. pp. 221-226
@inproceedings{a47131f299b040928d3a6a4e0147439a,
title = "A comparison of statistical and rule-based models for style-specific harmonization",
abstract = "The process of generating chords for harmonizing a melody with the goal of mimicking an artist's style is investigated in this paper. We compared and tested three different approaches, including a rule-based model, a statistical model, and a hybrid system of the two, for such tasks. Experiments were conducted using songs from seven stylistically identifiable pop/rock bands, and the chords generated by the systems were compared to the ones in the artists' original work. Evaluations were performed on multiple aspects, including calculating the average percentage of chords that were the same and those that were related, studying the manner in which the size of the training set affects the output harmonization, and examining a system's behaviors in terms of the ability of generating unseen chords and the number of unique chords produced per song. We observed that the rule-based system performs comparably well while the result of the system with learning capability varies as the training set grows.",
author = "Ching-Hua Chuan",
year = "2011",
month = "12",
day = "1",
language = "English (US)",
isbn = "9780615548654",
pages = "221--226",
booktitle = "Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011",

}

TY - GEN

T1 - A comparison of statistical and rule-based models for style-specific harmonization

AU - Chuan, Ching-Hua

PY - 2011/12/1

Y1 - 2011/12/1

N2 - The process of generating chords for harmonizing a melody with the goal of mimicking an artist's style is investigated in this paper. We compared and tested three different approaches, including a rule-based model, a statistical model, and a hybrid system of the two, for such tasks. Experiments were conducted using songs from seven stylistically identifiable pop/rock bands, and the chords generated by the systems were compared to the ones in the artists' original work. Evaluations were performed on multiple aspects, including calculating the average percentage of chords that were the same and those that were related, studying the manner in which the size of the training set affects the output harmonization, and examining a system's behaviors in terms of the ability of generating unseen chords and the number of unique chords produced per song. We observed that the rule-based system performs comparably well while the result of the system with learning capability varies as the training set grows.

AB - The process of generating chords for harmonizing a melody with the goal of mimicking an artist's style is investigated in this paper. We compared and tested three different approaches, including a rule-based model, a statistical model, and a hybrid system of the two, for such tasks. Experiments were conducted using songs from seven stylistically identifiable pop/rock bands, and the chords generated by the systems were compared to the ones in the artists' original work. Evaluations were performed on multiple aspects, including calculating the average percentage of chords that were the same and those that were related, studying the manner in which the size of the training set affects the output harmonization, and examining a system's behaviors in terms of the ability of generating unseen chords and the number of unique chords produced per song. We observed that the rule-based system performs comparably well while the result of the system with learning capability varies as the training set grows.

UR - http://www.scopus.com/inward/record.url?scp=84873592691&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873592691&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780615548654

SP - 221

EP - 226

BT - Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011

ER -