Instrument identification in polyphonic music: Feature weighting with mixed sounds, pitch-dependent timbre modeling, and use of musical context

Tetsuro Kitahara, Masataka Goto, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

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

14 Citations (Scopus)

Abstract

This paper addresses the problem of identifying musical instruments in polyphonic music. Musical instrument identification (MII) is an improtant task in music information retrieval because MII results make it possible to automatically retrieving certain types of music (e.g., piano sonata, string quartet). Only a few studies, however, have dealt with MII in polyphonic music. In MII in polyphonic music, there are three issues: feature variations caused by sound mixtures, the pitch dependency of timbres, and the use of musical context. For the first issue, templates of feature vectors representing timbres are extracted from not only isolated sounds but also sound mixtures. Because some features are not robust in the mixtures, features are weighted according to their robustness by using linear discriminant analysis. For the second issue, we use an F0-dependent multivariate normal distribution, which approximates the pitch dependency as a function of fundamental frequency. For the third issue, when the instrument of each note is identified, the a priori probablity of the note is calculated from the a posteriori probabilities of temporally neighboring notes. Experimental results showed that recognition rates were improved from 60.8% to 85.8% for trio music and from 65.5% to 91.1% for duo music.

Original languageEnglish
Title of host publicationISMIR 2005 - 6th International Conference on Music Information Retrieval
Pages558-563
Number of pages6
Publication statusPublished - 2005
Externally publishedYes
Event6th International Conference on Music Information Retrieval, ISMIR 2005 - London
Duration: 2005 Sep 112005 Sep 15

Other

Other6th International Conference on Music Information Retrieval, ISMIR 2005
CityLondon
Period05/9/1105/9/15

Fingerprint

Musical instruments
Acoustic waves
Discriminant analysis
Normal distribution
Information retrieval
Modeling
Musical Instruments
Music
Timbre
Sound
Polyphonic

Keywords

  • F0-dependent multivariate normal distribution
  • Mixedsound template
  • MPEG-7
  • Musical context
  • Musical instrument identification

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Kitahara, T., Goto, M., Komatani, K., Ogata, T., & Okuno, H. G. (2005). Instrument identification in polyphonic music: Feature weighting with mixed sounds, pitch-dependent timbre modeling, and use of musical context. In ISMIR 2005 - 6th International Conference on Music Information Retrieval (pp. 558-563)

Instrument identification in polyphonic music : Feature weighting with mixed sounds, pitch-dependent timbre modeling, and use of musical context. / Kitahara, Tetsuro; Goto, Masataka; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

ISMIR 2005 - 6th International Conference on Music Information Retrieval. 2005. p. 558-563.

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

Kitahara, T, Goto, M, Komatani, K, Ogata, T & Okuno, HG 2005, Instrument identification in polyphonic music: Feature weighting with mixed sounds, pitch-dependent timbre modeling, and use of musical context. in ISMIR 2005 - 6th International Conference on Music Information Retrieval. pp. 558-563, 6th International Conference on Music Information Retrieval, ISMIR 2005, London, 05/9/11.
Kitahara T, Goto M, Komatani K, Ogata T, Okuno HG. Instrument identification in polyphonic music: Feature weighting with mixed sounds, pitch-dependent timbre modeling, and use of musical context. In ISMIR 2005 - 6th International Conference on Music Information Retrieval. 2005. p. 558-563
Kitahara, Tetsuro ; Goto, Masataka ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Instrument identification in polyphonic music : Feature weighting with mixed sounds, pitch-dependent timbre modeling, and use of musical context. ISMIR 2005 - 6th International Conference on Music Information Retrieval. 2005. pp. 558-563
@inproceedings{92c18317fe7e41c9b1d5f2397bb71d17,
title = "Instrument identification in polyphonic music: Feature weighting with mixed sounds, pitch-dependent timbre modeling, and use of musical context",
abstract = "This paper addresses the problem of identifying musical instruments in polyphonic music. Musical instrument identification (MII) is an improtant task in music information retrieval because MII results make it possible to automatically retrieving certain types of music (e.g., piano sonata, string quartet). Only a few studies, however, have dealt with MII in polyphonic music. In MII in polyphonic music, there are three issues: feature variations caused by sound mixtures, the pitch dependency of timbres, and the use of musical context. For the first issue, templates of feature vectors representing timbres are extracted from not only isolated sounds but also sound mixtures. Because some features are not robust in the mixtures, features are weighted according to their robustness by using linear discriminant analysis. For the second issue, we use an F0-dependent multivariate normal distribution, which approximates the pitch dependency as a function of fundamental frequency. For the third issue, when the instrument of each note is identified, the a priori probablity of the note is calculated from the a posteriori probabilities of temporally neighboring notes. Experimental results showed that recognition rates were improved from 60.8{\%} to 85.8{\%} for trio music and from 65.5{\%} to 91.1{\%} for duo music.",
keywords = "F0-dependent multivariate normal distribution, Mixedsound template, MPEG-7, Musical context, Musical instrument identification",
author = "Tetsuro Kitahara and Masataka Goto and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2005",
language = "English",
isbn = "9780955117909",
pages = "558--563",
booktitle = "ISMIR 2005 - 6th International Conference on Music Information Retrieval",

}

TY - GEN

T1 - Instrument identification in polyphonic music

T2 - Feature weighting with mixed sounds, pitch-dependent timbre modeling, and use of musical context

AU - Kitahara, Tetsuro

AU - Goto, Masataka

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2005

Y1 - 2005

N2 - This paper addresses the problem of identifying musical instruments in polyphonic music. Musical instrument identification (MII) is an improtant task in music information retrieval because MII results make it possible to automatically retrieving certain types of music (e.g., piano sonata, string quartet). Only a few studies, however, have dealt with MII in polyphonic music. In MII in polyphonic music, there are three issues: feature variations caused by sound mixtures, the pitch dependency of timbres, and the use of musical context. For the first issue, templates of feature vectors representing timbres are extracted from not only isolated sounds but also sound mixtures. Because some features are not robust in the mixtures, features are weighted according to their robustness by using linear discriminant analysis. For the second issue, we use an F0-dependent multivariate normal distribution, which approximates the pitch dependency as a function of fundamental frequency. For the third issue, when the instrument of each note is identified, the a priori probablity of the note is calculated from the a posteriori probabilities of temporally neighboring notes. Experimental results showed that recognition rates were improved from 60.8% to 85.8% for trio music and from 65.5% to 91.1% for duo music.

AB - This paper addresses the problem of identifying musical instruments in polyphonic music. Musical instrument identification (MII) is an improtant task in music information retrieval because MII results make it possible to automatically retrieving certain types of music (e.g., piano sonata, string quartet). Only a few studies, however, have dealt with MII in polyphonic music. In MII in polyphonic music, there are three issues: feature variations caused by sound mixtures, the pitch dependency of timbres, and the use of musical context. For the first issue, templates of feature vectors representing timbres are extracted from not only isolated sounds but also sound mixtures. Because some features are not robust in the mixtures, features are weighted according to their robustness by using linear discriminant analysis. For the second issue, we use an F0-dependent multivariate normal distribution, which approximates the pitch dependency as a function of fundamental frequency. For the third issue, when the instrument of each note is identified, the a priori probablity of the note is calculated from the a posteriori probabilities of temporally neighboring notes. Experimental results showed that recognition rates were improved from 60.8% to 85.8% for trio music and from 65.5% to 91.1% for duo music.

KW - F0-dependent multivariate normal distribution

KW - Mixedsound template

KW - MPEG-7

KW - Musical context

KW - Musical instrument identification

UR - http://www.scopus.com/inward/record.url?scp=33846174759&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846174759&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33846174759

SN - 9780955117909

SP - 558

EP - 563

BT - ISMIR 2005 - 6th International Conference on Music Information Retrieval

ER -