Musical instrument recognizer "instrogram" and its application to music retrieval based on instrumentation similarity

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

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

16 Citations (Scopus)

Abstract

Instrumentation is an important cue in retrieving musical content. Conventional methods for instrument recognition performing notewise require accurate estimation of the onset time and fundamental frequency (F0) for each note, which is not easy in polyphonic music. This paper presents a non-notewise method for instrument recognition in polyphonic musical audio signals. Instead of such note-wise estimation, our method calculates the temporal trajectory of instrument existence probabilities for every F0 and visualizes it as a spectrogram-like graphical representation, called an instrogram. This method can avoid the influence by errors of onset detection and F0 estimation because it does not use them. We also present methods for MPEG-7-based instrument annotation and music information retrieval based on the similarity between instrograms. Experimental results with realistic music show the average accuracy of 76.2% for the instrument annotation and that the instrogram-based similarity measure represents the actual instrumentation similarity better than an MFCC-based one.

Original languageEnglish
Title of host publicationISM 2006 - 8th IEEE International Symposium on Multimedia
Pages265-272
Number of pages8
DOIs
Publication statusPublished - 2006
Externally publishedYes
EventISM 2006 - 8th IEEE International Symposium on Multimedia - San Diego, CA
Duration: 2006 Dec 112006 Dec 13

Other

OtherISM 2006 - 8th IEEE International Symposium on Multimedia
CitySan Diego, CA
Period06/12/1106/12/13

Fingerprint

Musical instruments
Information retrieval
Trajectories

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Kitahara, T., Goto, M., Komatani, K., Ogata, T., & Okuno, H. G. (2006). Musical instrument recognizer "instrogram" and its application to music retrieval based on instrumentation similarity. In ISM 2006 - 8th IEEE International Symposium on Multimedia (pp. 265-272). [4061177] https://doi.org/10.1109/ISM.2006.113

Musical instrument recognizer "instrogram" and its application to music retrieval based on instrumentation similarity. / Kitahara, Tetsuro; Goto, Masataka; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

ISM 2006 - 8th IEEE International Symposium on Multimedia. 2006. p. 265-272 4061177.

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

Kitahara, T, Goto, M, Komatani, K, Ogata, T & Okuno, HG 2006, Musical instrument recognizer "instrogram" and its application to music retrieval based on instrumentation similarity. in ISM 2006 - 8th IEEE International Symposium on Multimedia., 4061177, pp. 265-272, ISM 2006 - 8th IEEE International Symposium on Multimedia, San Diego, CA, 06/12/11. https://doi.org/10.1109/ISM.2006.113
Kitahara T, Goto M, Komatani K, Ogata T, Okuno HG. Musical instrument recognizer "instrogram" and its application to music retrieval based on instrumentation similarity. In ISM 2006 - 8th IEEE International Symposium on Multimedia. 2006. p. 265-272. 4061177 https://doi.org/10.1109/ISM.2006.113
Kitahara, Tetsuro ; Goto, Masataka ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Musical instrument recognizer "instrogram" and its application to music retrieval based on instrumentation similarity. ISM 2006 - 8th IEEE International Symposium on Multimedia. 2006. pp. 265-272
@inproceedings{2b396bc2d6f24fa2baef06087fc3aaf7,
title = "Musical instrument recognizer {"}instrogram{"} and its application to music retrieval based on instrumentation similarity",
abstract = "Instrumentation is an important cue in retrieving musical content. Conventional methods for instrument recognition performing notewise require accurate estimation of the onset time and fundamental frequency (F0) for each note, which is not easy in polyphonic music. This paper presents a non-notewise method for instrument recognition in polyphonic musical audio signals. Instead of such note-wise estimation, our method calculates the temporal trajectory of instrument existence probabilities for every F0 and visualizes it as a spectrogram-like graphical representation, called an instrogram. This method can avoid the influence by errors of onset detection and F0 estimation because it does not use them. We also present methods for MPEG-7-based instrument annotation and music information retrieval based on the similarity between instrograms. Experimental results with realistic music show the average accuracy of 76.2{\%} for the instrument annotation and that the instrogram-based similarity measure represents the actual instrumentation similarity better than an MFCC-based one.",
author = "Tetsuro Kitahara and Masataka Goto and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2006",
doi = "10.1109/ISM.2006.113",
language = "English",
isbn = "0769527469",
pages = "265--272",
booktitle = "ISM 2006 - 8th IEEE International Symposium on Multimedia",

}

TY - GEN

T1 - Musical instrument recognizer "instrogram" and its application to music retrieval based on instrumentation similarity

AU - Kitahara, Tetsuro

AU - Goto, Masataka

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2006

Y1 - 2006

N2 - Instrumentation is an important cue in retrieving musical content. Conventional methods for instrument recognition performing notewise require accurate estimation of the onset time and fundamental frequency (F0) for each note, which is not easy in polyphonic music. This paper presents a non-notewise method for instrument recognition in polyphonic musical audio signals. Instead of such note-wise estimation, our method calculates the temporal trajectory of instrument existence probabilities for every F0 and visualizes it as a spectrogram-like graphical representation, called an instrogram. This method can avoid the influence by errors of onset detection and F0 estimation because it does not use them. We also present methods for MPEG-7-based instrument annotation and music information retrieval based on the similarity between instrograms. Experimental results with realistic music show the average accuracy of 76.2% for the instrument annotation and that the instrogram-based similarity measure represents the actual instrumentation similarity better than an MFCC-based one.

AB - Instrumentation is an important cue in retrieving musical content. Conventional methods for instrument recognition performing notewise require accurate estimation of the onset time and fundamental frequency (F0) for each note, which is not easy in polyphonic music. This paper presents a non-notewise method for instrument recognition in polyphonic musical audio signals. Instead of such note-wise estimation, our method calculates the temporal trajectory of instrument existence probabilities for every F0 and visualizes it as a spectrogram-like graphical representation, called an instrogram. This method can avoid the influence by errors of onset detection and F0 estimation because it does not use them. We also present methods for MPEG-7-based instrument annotation and music information retrieval based on the similarity between instrograms. Experimental results with realistic music show the average accuracy of 76.2% for the instrument annotation and that the instrogram-based similarity measure represents the actual instrumentation similarity better than an MFCC-based one.

UR - http://www.scopus.com/inward/record.url?scp=46249124867&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46249124867&partnerID=8YFLogxK

U2 - 10.1109/ISM.2006.113

DO - 10.1109/ISM.2006.113

M3 - Conference contribution

SN - 0769527469

SN - 9780769527468

SP - 265

EP - 272

BT - ISM 2006 - 8th IEEE International Symposium on Multimedia

ER -