Automatic feature weighting in automatic transcription of specified part in polyphonic music

Katsutoshi Itoyama, Tetsuro Kitahara, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

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

Abstract

We studied the problem of automatic music transcription (AMT) for polyphonic music. AMT is an important task for music information retrieval because AMT results enable retrieving musical pieces, high-level annotation, demixing, etc. We attempted to transcribe a part played by an instrument specified by users (specified part tracking). Only two timbre models are required in the specified part tracking to identify the specified musical instrument even when the number of instruments increases. This transcription is formulated into a time-series classification problem with multiple features. We furthermore attempted to automatically estimate weights of the features, because the importance of these features varies for each musical signal. We estimated quasi-optimal weights of the features using a genetic algorithm for each musical signal. We tested our AMT system using trio stereo musical signals. Accuracies with our feature weighting method were 69.8% on average, whereas those without feature weighting were 66.0%.

Original languageEnglish
Title of host publicationISMIR 2006 - 7th International Conference on Music Information Retrieval
Pages172-175
Number of pages4
Publication statusPublished - 2006
Externally publishedYes
Event7th International Conference on Music Information Retrieval, ISMIR 2006 - Victoria, BC
Duration: 2006 Oct 82006 Oct 12

Other

Other7th International Conference on Music Information Retrieval, ISMIR 2006
CityVictoria, BC
Period06/10/806/10/12

Fingerprint

Transcription
Musical instruments
Information retrieval
Time series
Genetic algorithms
Polyphonic
Music

Keywords

  • Automatic music transcription
  • Feature weighting
  • Genetic algorithm
  • Specified part tracking

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Itoyama, K., Kitahara, T., Komatani, K., Ogata, T., & Okuno, H. G. (2006). Automatic feature weighting in automatic transcription of specified part in polyphonic music. In ISMIR 2006 - 7th International Conference on Music Information Retrieval (pp. 172-175)

Automatic feature weighting in automatic transcription of specified part in polyphonic music. / Itoyama, Katsutoshi; Kitahara, Tetsuro; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

ISMIR 2006 - 7th International Conference on Music Information Retrieval. 2006. p. 172-175.

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

Itoyama, K, Kitahara, T, Komatani, K, Ogata, T & Okuno, HG 2006, Automatic feature weighting in automatic transcription of specified part in polyphonic music. in ISMIR 2006 - 7th International Conference on Music Information Retrieval. pp. 172-175, 7th International Conference on Music Information Retrieval, ISMIR 2006, Victoria, BC, 06/10/8.
Itoyama K, Kitahara T, Komatani K, Ogata T, Okuno HG. Automatic feature weighting in automatic transcription of specified part in polyphonic music. In ISMIR 2006 - 7th International Conference on Music Information Retrieval. 2006. p. 172-175
Itoyama, Katsutoshi ; Kitahara, Tetsuro ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Automatic feature weighting in automatic transcription of specified part in polyphonic music. ISMIR 2006 - 7th International Conference on Music Information Retrieval. 2006. pp. 172-175
@inproceedings{20ea11000fd64936b7cf7e37a45d341a,
title = "Automatic feature weighting in automatic transcription of specified part in polyphonic music",
abstract = "We studied the problem of automatic music transcription (AMT) for polyphonic music. AMT is an important task for music information retrieval because AMT results enable retrieving musical pieces, high-level annotation, demixing, etc. We attempted to transcribe a part played by an instrument specified by users (specified part tracking). Only two timbre models are required in the specified part tracking to identify the specified musical instrument even when the number of instruments increases. This transcription is formulated into a time-series classification problem with multiple features. We furthermore attempted to automatically estimate weights of the features, because the importance of these features varies for each musical signal. We estimated quasi-optimal weights of the features using a genetic algorithm for each musical signal. We tested our AMT system using trio stereo musical signals. Accuracies with our feature weighting method were 69.8{\%} on average, whereas those without feature weighting were 66.0{\%}.",
keywords = "Automatic music transcription, Feature weighting, Genetic algorithm, Specified part tracking",
author = "Katsutoshi Itoyama and Tetsuro Kitahara and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2006",
language = "English",
isbn = "9781550583496",
pages = "172--175",
booktitle = "ISMIR 2006 - 7th International Conference on Music Information Retrieval",

}

TY - GEN

T1 - Automatic feature weighting in automatic transcription of specified part in polyphonic music

AU - Itoyama, Katsutoshi

AU - Kitahara, Tetsuro

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2006

Y1 - 2006

N2 - We studied the problem of automatic music transcription (AMT) for polyphonic music. AMT is an important task for music information retrieval because AMT results enable retrieving musical pieces, high-level annotation, demixing, etc. We attempted to transcribe a part played by an instrument specified by users (specified part tracking). Only two timbre models are required in the specified part tracking to identify the specified musical instrument even when the number of instruments increases. This transcription is formulated into a time-series classification problem with multiple features. We furthermore attempted to automatically estimate weights of the features, because the importance of these features varies for each musical signal. We estimated quasi-optimal weights of the features using a genetic algorithm for each musical signal. We tested our AMT system using trio stereo musical signals. Accuracies with our feature weighting method were 69.8% on average, whereas those without feature weighting were 66.0%.

AB - We studied the problem of automatic music transcription (AMT) for polyphonic music. AMT is an important task for music information retrieval because AMT results enable retrieving musical pieces, high-level annotation, demixing, etc. We attempted to transcribe a part played by an instrument specified by users (specified part tracking). Only two timbre models are required in the specified part tracking to identify the specified musical instrument even when the number of instruments increases. This transcription is formulated into a time-series classification problem with multiple features. We furthermore attempted to automatically estimate weights of the features, because the importance of these features varies for each musical signal. We estimated quasi-optimal weights of the features using a genetic algorithm for each musical signal. We tested our AMT system using trio stereo musical signals. Accuracies with our feature weighting method were 69.8% on average, whereas those without feature weighting were 66.0%.

KW - Automatic music transcription

KW - Feature weighting

KW - Genetic algorithm

KW - Specified part tracking

UR - http://www.scopus.com/inward/record.url?scp=84873482135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873482135&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781550583496

SP - 172

EP - 175

BT - ISMIR 2006 - 7th International Conference on Music Information Retrieval

ER -