Automatic chord recognition based on probabilistic integration of chord transition and bass pitch estimation

Kouhei Sumi, Katsutoshi Itoyama, Kazuyoshi Yoshii, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

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

15 Citations (Scopus)

Abstract

This paper presents a method that identifies musical chords in polyphonic musical signals. As musical chords mainly represent the harmony of music and are related to other musical elements such as melody and rhythm, the performance of chord recognition should improve if this interrelationship is taken into consideration. Nevertheless, this interrelationship has not been utilized in the literature as far as the authors are aware. In this paper, bass lines are utilized as clues for improving chord recognition because they can be regarded as an element of the melody. A probabilistic framework is devised to uniformly integrate bass lines extracted by using bass pitch estimation into a hypothesis-search-based chord recognition. To prune the hypothesis space of the search, the hypothesis reliability is defined as the weighted sum of three reliabilities: the likelihood of Gaussian Mixture Models for the observed features, the joint probability of chord and bass pitch, and the chord transition N-gram probability. Experimental results show that our method recognized the chord sequences of 150 songs in twelve Beatles albums; the average frame-rate accuracy of the results was 73.4%.

Original languageEnglish
Title of host publicationISMIR 2008 - 9th International Conference on Music Information Retrieval
Pages39-44
Number of pages6
Publication statusPublished - 2008
Externally publishedYes
Event9th International Conference on Music Information Retrieval, ISMIR 2008 - Philadelphia, PA
Duration: 2008 Sep 142008 Sep 18

Other

Other9th International Conference on Music Information Retrieval, ISMIR 2008
CityPhiladelphia, PA
Period08/9/1408/9/18

Fingerprint

Chord
Melody
Interrelationship
N-gram
Mixture Model
Song
Polyphonic
Music
The Beatles
Rhythm
Musical Elements
Harmony
Albums

Keywords

  • Bass line
  • Chord recognition
  • Hypothesis search
  • Probabilistic integration

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Sumi, K., Itoyama, K., Yoshii, K., Komatani, K., Ogata, T., & Okuno, H. G. (2008). Automatic chord recognition based on probabilistic integration of chord transition and bass pitch estimation. In ISMIR 2008 - 9th International Conference on Music Information Retrieval (pp. 39-44)

Automatic chord recognition based on probabilistic integration of chord transition and bass pitch estimation. / Sumi, Kouhei; Itoyama, Katsutoshi; Yoshii, Kazuyoshi; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

ISMIR 2008 - 9th International Conference on Music Information Retrieval. 2008. p. 39-44.

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

Sumi, K, Itoyama, K, Yoshii, K, Komatani, K, Ogata, T & Okuno, HG 2008, Automatic chord recognition based on probabilistic integration of chord transition and bass pitch estimation. in ISMIR 2008 - 9th International Conference on Music Information Retrieval. pp. 39-44, 9th International Conference on Music Information Retrieval, ISMIR 2008, Philadelphia, PA, 08/9/14.
Sumi K, Itoyama K, Yoshii K, Komatani K, Ogata T, Okuno HG. Automatic chord recognition based on probabilistic integration of chord transition and bass pitch estimation. In ISMIR 2008 - 9th International Conference on Music Information Retrieval. 2008. p. 39-44
Sumi, Kouhei ; Itoyama, Katsutoshi ; Yoshii, Kazuyoshi ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Automatic chord recognition based on probabilistic integration of chord transition and bass pitch estimation. ISMIR 2008 - 9th International Conference on Music Information Retrieval. 2008. pp. 39-44
@inproceedings{3de98dc1c9dd4625adce99f53911c63a,
title = "Automatic chord recognition based on probabilistic integration of chord transition and bass pitch estimation",
abstract = "This paper presents a method that identifies musical chords in polyphonic musical signals. As musical chords mainly represent the harmony of music and are related to other musical elements such as melody and rhythm, the performance of chord recognition should improve if this interrelationship is taken into consideration. Nevertheless, this interrelationship has not been utilized in the literature as far as the authors are aware. In this paper, bass lines are utilized as clues for improving chord recognition because they can be regarded as an element of the melody. A probabilistic framework is devised to uniformly integrate bass lines extracted by using bass pitch estimation into a hypothesis-search-based chord recognition. To prune the hypothesis space of the search, the hypothesis reliability is defined as the weighted sum of three reliabilities: the likelihood of Gaussian Mixture Models for the observed features, the joint probability of chord and bass pitch, and the chord transition N-gram probability. Experimental results show that our method recognized the chord sequences of 150 songs in twelve Beatles albums; the average frame-rate accuracy of the results was 73.4{\%}.",
keywords = "Bass line, Chord recognition, Hypothesis search, Probabilistic integration",
author = "Kouhei Sumi and Katsutoshi Itoyama and Kazuyoshi Yoshii and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2008",
language = "English",
isbn = "9780615248493",
pages = "39--44",
booktitle = "ISMIR 2008 - 9th International Conference on Music Information Retrieval",

}

TY - GEN

T1 - Automatic chord recognition based on probabilistic integration of chord transition and bass pitch estimation

AU - Sumi, Kouhei

AU - Itoyama, Katsutoshi

AU - Yoshii, Kazuyoshi

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2008

Y1 - 2008

N2 - This paper presents a method that identifies musical chords in polyphonic musical signals. As musical chords mainly represent the harmony of music and are related to other musical elements such as melody and rhythm, the performance of chord recognition should improve if this interrelationship is taken into consideration. Nevertheless, this interrelationship has not been utilized in the literature as far as the authors are aware. In this paper, bass lines are utilized as clues for improving chord recognition because they can be regarded as an element of the melody. A probabilistic framework is devised to uniformly integrate bass lines extracted by using bass pitch estimation into a hypothesis-search-based chord recognition. To prune the hypothesis space of the search, the hypothesis reliability is defined as the weighted sum of three reliabilities: the likelihood of Gaussian Mixture Models for the observed features, the joint probability of chord and bass pitch, and the chord transition N-gram probability. Experimental results show that our method recognized the chord sequences of 150 songs in twelve Beatles albums; the average frame-rate accuracy of the results was 73.4%.

AB - This paper presents a method that identifies musical chords in polyphonic musical signals. As musical chords mainly represent the harmony of music and are related to other musical elements such as melody and rhythm, the performance of chord recognition should improve if this interrelationship is taken into consideration. Nevertheless, this interrelationship has not been utilized in the literature as far as the authors are aware. In this paper, bass lines are utilized as clues for improving chord recognition because they can be regarded as an element of the melody. A probabilistic framework is devised to uniformly integrate bass lines extracted by using bass pitch estimation into a hypothesis-search-based chord recognition. To prune the hypothesis space of the search, the hypothesis reliability is defined as the weighted sum of three reliabilities: the likelihood of Gaussian Mixture Models for the observed features, the joint probability of chord and bass pitch, and the chord transition N-gram probability. Experimental results show that our method recognized the chord sequences of 150 songs in twelve Beatles albums; the average frame-rate accuracy of the results was 73.4%.

KW - Bass line

KW - Chord recognition

KW - Hypothesis search

KW - Probabilistic integration

UR - http://www.scopus.com/inward/record.url?scp=80052068532&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052068532&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80052068532

SN - 9780615248493

SP - 39

EP - 44

BT - ISMIR 2008 - 9th International Conference on Music Information Retrieval

ER -