Polyphonic music classification on symbolic data using dissimilarity functions

Yoko Anan, kohei hatano, Hideo Bannai, Masayuki Takeda, Ken Satoh

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

4 Citations (Scopus)

Abstract

This paper addresses the polyphonic music classification problem on symbolic data. A new method is proposed which converts music pieces into binary chroma vector sequences and then classifies them by applying the dissimilarity-based classification method TWIST proposed in our previous work. One advantage of using TWIST is that it works with any dissimilarity measure. Computational experiments show that the proposed method drastically outperforms SVM and k-NN, the state-of-the-art classification methods.

Original languageEnglish
Title of host publicationProceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012
Pages229-234
Number of pages6
Publication statusPublished - 2012
Event13th International Society for Music Information Retrieval Conference, ISMIR 2012 - Porto, Portugal
Duration: Oct 8 2012Oct 12 2012

Other

Other13th International Society for Music Information Retrieval Conference, ISMIR 2012
CountryPortugal
CityPorto
Period10/8/1210/12/12

Fingerprint

Music
Polyphonic
Experiments
Computational
Convert
Chroma
Experiment

All Science Journal Classification (ASJC) codes

  • Music
  • Information Systems

Cite this

Anan, Y., hatano, K., Bannai, H., Takeda, M., & Satoh, K. (2012). Polyphonic music classification on symbolic data using dissimilarity functions. In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012 (pp. 229-234)

Polyphonic music classification on symbolic data using dissimilarity functions. / Anan, Yoko; hatano, kohei; Bannai, Hideo; Takeda, Masayuki; Satoh, Ken.

Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. p. 229-234.

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

Anan, Y, hatano, K, Bannai, H, Takeda, M & Satoh, K 2012, Polyphonic music classification on symbolic data using dissimilarity functions. in Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. pp. 229-234, 13th International Society for Music Information Retrieval Conference, ISMIR 2012, Porto, Portugal, 10/8/12.
Anan Y, hatano K, Bannai H, Takeda M, Satoh K. Polyphonic music classification on symbolic data using dissimilarity functions. In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. p. 229-234
Anan, Yoko ; hatano, kohei ; Bannai, Hideo ; Takeda, Masayuki ; Satoh, Ken. / Polyphonic music classification on symbolic data using dissimilarity functions. Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. pp. 229-234
@inproceedings{c249539773ba40ee99e888167688b758,
title = "Polyphonic music classification on symbolic data using dissimilarity functions",
abstract = "This paper addresses the polyphonic music classification problem on symbolic data. A new method is proposed which converts music pieces into binary chroma vector sequences and then classifies them by applying the dissimilarity-based classification method TWIST proposed in our previous work. One advantage of using TWIST is that it works with any dissimilarity measure. Computational experiments show that the proposed method drastically outperforms SVM and k-NN, the state-of-the-art classification methods.",
author = "Yoko Anan and kohei hatano and Hideo Bannai and Masayuki Takeda and Ken Satoh",
year = "2012",
language = "English",
isbn = "9789727521449",
pages = "229--234",
booktitle = "Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012",

}

TY - GEN

T1 - Polyphonic music classification on symbolic data using dissimilarity functions

AU - Anan, Yoko

AU - hatano, kohei

AU - Bannai, Hideo

AU - Takeda, Masayuki

AU - Satoh, Ken

PY - 2012

Y1 - 2012

N2 - This paper addresses the polyphonic music classification problem on symbolic data. A new method is proposed which converts music pieces into binary chroma vector sequences and then classifies them by applying the dissimilarity-based classification method TWIST proposed in our previous work. One advantage of using TWIST is that it works with any dissimilarity measure. Computational experiments show that the proposed method drastically outperforms SVM and k-NN, the state-of-the-art classification methods.

AB - This paper addresses the polyphonic music classification problem on symbolic data. A new method is proposed which converts music pieces into binary chroma vector sequences and then classifies them by applying the dissimilarity-based classification method TWIST proposed in our previous work. One advantage of using TWIST is that it works with any dissimilarity measure. Computational experiments show that the proposed method drastically outperforms SVM and k-NN, the state-of-the-art classification methods.

UR - http://www.scopus.com/inward/record.url?scp=84873415756&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873415756&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84873415756

SN - 9789727521449

SP - 229

EP - 234

BT - Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012

ER -