A feature smoothing method for chord recognition using recurrence plots

Taemin Cho, Juan P. Bello

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

Abstract

In this paper, we propose a feature smoothing technique for chord recognition tasks based on repeated patterns within a song. By only considering repeated segments of a song, our method can smooth the features without losing chord boundary information and fine details of the original feature. While a similar existing technique requires several hard decisions such as beat quantization and segmentation, our method uses a simple pragmatic approach based on recurrence plot to decide which repeated parts to include in the smoothing process. This approach uses a more formal definition of the repetition search and allows shorter ("chordsize") repeated segments to contribute to the feature improvement process. In our experiments, our method outperforms conventional and popular smoothing techniques (a moving average filter and a median filter). In particular, it shows a synergistic effect when used with the Viterbi decoder.

Original languageEnglish (US)
Title of host publicationProceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011
Pages651-656
Number of pages6
StatePublished - 2011
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

Median filters
Experiments
Smoothing Methods
Chord
Plot
Filter
Song

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Cho, T., & Bello, J. P. (2011). A feature smoothing method for chord recognition using recurrence plots. In Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011 (pp. 651-656)

A feature smoothing method for chord recognition using recurrence plots. / Cho, Taemin; Bello, Juan P.

Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011. 2011. p. 651-656.

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

Cho, T & Bello, JP 2011, A feature smoothing method for chord recognition using recurrence plots. in Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011. pp. 651-656, 12th International Society for Music Information Retrieval Conference, ISMIR 2011, Miami, FL, United States, 10/24/11.
Cho T, Bello JP. A feature smoothing method for chord recognition using recurrence plots. In Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011. 2011. p. 651-656
Cho, Taemin ; Bello, Juan P. / A feature smoothing method for chord recognition using recurrence plots. Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011. 2011. pp. 651-656
@inproceedings{72f0bdcc67fb42c5850c758fc35f491b,
title = "A feature smoothing method for chord recognition using recurrence plots",
abstract = "In this paper, we propose a feature smoothing technique for chord recognition tasks based on repeated patterns within a song. By only considering repeated segments of a song, our method can smooth the features without losing chord boundary information and fine details of the original feature. While a similar existing technique requires several hard decisions such as beat quantization and segmentation, our method uses a simple pragmatic approach based on recurrence plot to decide which repeated parts to include in the smoothing process. This approach uses a more formal definition of the repetition search and allows shorter ({"}chordsize{"}) repeated segments to contribute to the feature improvement process. In our experiments, our method outperforms conventional and popular smoothing techniques (a moving average filter and a median filter). In particular, it shows a synergistic effect when used with the Viterbi decoder.",
author = "Taemin Cho and Bello, {Juan P.}",
year = "2011",
language = "English (US)",
isbn = "9780615548654",
pages = "651--656",
booktitle = "Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011",

}

TY - GEN

T1 - A feature smoothing method for chord recognition using recurrence plots

AU - Cho, Taemin

AU - Bello, Juan P.

PY - 2011

Y1 - 2011

N2 - In this paper, we propose a feature smoothing technique for chord recognition tasks based on repeated patterns within a song. By only considering repeated segments of a song, our method can smooth the features without losing chord boundary information and fine details of the original feature. While a similar existing technique requires several hard decisions such as beat quantization and segmentation, our method uses a simple pragmatic approach based on recurrence plot to decide which repeated parts to include in the smoothing process. This approach uses a more formal definition of the repetition search and allows shorter ("chordsize") repeated segments to contribute to the feature improvement process. In our experiments, our method outperforms conventional and popular smoothing techniques (a moving average filter and a median filter). In particular, it shows a synergistic effect when used with the Viterbi decoder.

AB - In this paper, we propose a feature smoothing technique for chord recognition tasks based on repeated patterns within a song. By only considering repeated segments of a song, our method can smooth the features without losing chord boundary information and fine details of the original feature. While a similar existing technique requires several hard decisions such as beat quantization and segmentation, our method uses a simple pragmatic approach based on recurrence plot to decide which repeated parts to include in the smoothing process. This approach uses a more formal definition of the repetition search and allows shorter ("chordsize") repeated segments to contribute to the feature improvement process. In our experiments, our method outperforms conventional and popular smoothing techniques (a moving average filter and a median filter). In particular, it shows a synergistic effect when used with the Viterbi decoder.

UR - http://www.scopus.com/inward/record.url?scp=84873375453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873375453&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780615548654

SP - 651

EP - 656

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

ER -