Pitch-dependent identification of musical instrument sounds

Tetsuro Kitahara, Masataka Goto, Hiroshi G. Okuno

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

This paper describes a musical instrument identification method that takes into consideration the pitch dependency of timbres of musical instruments. The difficulty in musical instrument identification resides in the pitch dependency of musical instrument sounds, that is, acoustic features of most musical instruments vary according to the pitch (fundamental frequency, F0). To cope with this difficulty, we propose an F0-dependent multivariate normal distribution, where each element of the mean vector is represented by a function of F0. Our method first extracts 129 features (e.g., the spectral centroid, the gradient of the straight line approximating the power envelope) from a musical instrument sound and then reduces the dimensionality of the feature space into 18 dimension. In the 18-dimensional feature space, it calculates an F0-dependent mean function and an F0-normalized covariance, and finally applies the Bayes decision rule. Experimental results of identifying 6,247 solo tones of 19 musical instruments shows that the proposed method improved the recognition rate from 75.73% to 79.73%.

Original languageEnglish
Pages (from-to)267-275
Number of pages9
JournalApplied Intelligence
Volume23
Issue number3
DOIs
Publication statusPublished - 2005 Dec
Externally publishedYes

Fingerprint

Musical instruments
Acoustic waves
Normal distribution
Acoustics

Keywords

  • Automatic music transcription
  • Computational auditory scene analysis
  • Fundamental frequency
  • Musical instrument identification
  • The pitch dependency

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence

Cite this

Pitch-dependent identification of musical instrument sounds. / Kitahara, Tetsuro; Goto, Masataka; Okuno, Hiroshi G.

In: Applied Intelligence, Vol. 23, No. 3, 12.2005, p. 267-275.

Research output: Contribution to journalArticle

Kitahara, Tetsuro ; Goto, Masataka ; Okuno, Hiroshi G. / Pitch-dependent identification of musical instrument sounds. In: Applied Intelligence. 2005 ; Vol. 23, No. 3. pp. 267-275.
@article{e2b0a90fc441426a943b0f5837d5dde0,
title = "Pitch-dependent identification of musical instrument sounds",
abstract = "This paper describes a musical instrument identification method that takes into consideration the pitch dependency of timbres of musical instruments. The difficulty in musical instrument identification resides in the pitch dependency of musical instrument sounds, that is, acoustic features of most musical instruments vary according to the pitch (fundamental frequency, F0). To cope with this difficulty, we propose an F0-dependent multivariate normal distribution, where each element of the mean vector is represented by a function of F0. Our method first extracts 129 features (e.g., the spectral centroid, the gradient of the straight line approximating the power envelope) from a musical instrument sound and then reduces the dimensionality of the feature space into 18 dimension. In the 18-dimensional feature space, it calculates an F0-dependent mean function and an F0-normalized covariance, and finally applies the Bayes decision rule. Experimental results of identifying 6,247 solo tones of 19 musical instruments shows that the proposed method improved the recognition rate from 75.73{\%} to 79.73{\%}.",
keywords = "Automatic music transcription, Computational auditory scene analysis, Fundamental frequency, Musical instrument identification, The pitch dependency",
author = "Tetsuro Kitahara and Masataka Goto and Okuno, {Hiroshi G.}",
year = "2005",
month = "12",
doi = "10.1007/s10489-005-4612-1",
language = "English",
volume = "23",
pages = "267--275",
journal = "Applied Intelligence",
issn = "0924-669X",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Pitch-dependent identification of musical instrument sounds

AU - Kitahara, Tetsuro

AU - Goto, Masataka

AU - Okuno, Hiroshi G.

PY - 2005/12

Y1 - 2005/12

N2 - This paper describes a musical instrument identification method that takes into consideration the pitch dependency of timbres of musical instruments. The difficulty in musical instrument identification resides in the pitch dependency of musical instrument sounds, that is, acoustic features of most musical instruments vary according to the pitch (fundamental frequency, F0). To cope with this difficulty, we propose an F0-dependent multivariate normal distribution, where each element of the mean vector is represented by a function of F0. Our method first extracts 129 features (e.g., the spectral centroid, the gradient of the straight line approximating the power envelope) from a musical instrument sound and then reduces the dimensionality of the feature space into 18 dimension. In the 18-dimensional feature space, it calculates an F0-dependent mean function and an F0-normalized covariance, and finally applies the Bayes decision rule. Experimental results of identifying 6,247 solo tones of 19 musical instruments shows that the proposed method improved the recognition rate from 75.73% to 79.73%.

AB - This paper describes a musical instrument identification method that takes into consideration the pitch dependency of timbres of musical instruments. The difficulty in musical instrument identification resides in the pitch dependency of musical instrument sounds, that is, acoustic features of most musical instruments vary according to the pitch (fundamental frequency, F0). To cope with this difficulty, we propose an F0-dependent multivariate normal distribution, where each element of the mean vector is represented by a function of F0. Our method first extracts 129 features (e.g., the spectral centroid, the gradient of the straight line approximating the power envelope) from a musical instrument sound and then reduces the dimensionality of the feature space into 18 dimension. In the 18-dimensional feature space, it calculates an F0-dependent mean function and an F0-normalized covariance, and finally applies the Bayes decision rule. Experimental results of identifying 6,247 solo tones of 19 musical instruments shows that the proposed method improved the recognition rate from 75.73% to 79.73%.

KW - Automatic music transcription

KW - Computational auditory scene analysis

KW - Fundamental frequency

KW - Musical instrument identification

KW - The pitch dependency

UR - http://www.scopus.com/inward/record.url?scp=29144452868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29144452868&partnerID=8YFLogxK

U2 - 10.1007/s10489-005-4612-1

DO - 10.1007/s10489-005-4612-1

M3 - Article

AN - SCOPUS:29144452868

VL - 23

SP - 267

EP - 275

JO - Applied Intelligence

JF - Applied Intelligence

SN - 0924-669X

IS - 3

ER -