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 Dec 1
Externally publishedYes
Event7th International Conference on Music Information Retrieval, ISMIR 2006 - Victoria, BC, Canada
Duration: 2006 Oct 82006 Oct 12

Publication series

NameISMIR 2006 - 7th International Conference on Music Information Retrieval

Conference

Conference7th International Conference on Music Information Retrieval, ISMIR 2006
CountryCanada
CityVictoria, BC
Period06/10/806/10/12

Keywords

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

ASJC Scopus subject areas

  • Music
  • Information Systems

Fingerprint Dive into the research topics of 'Automatic feature weighting in automatic transcription of specified part in polyphonic music'. Together they form a unique fingerprint.

  • 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). (ISMIR 2006 - 7th International Conference on Music Information Retrieval).