Bowed string sequence estimation of a violin based on adaptive audio signal classification and context-dependent error correction

Akira Maezawa, Katsutoshi Itoyama, Toru Takahashi, Tetsuya Ogata, Hiroshi G. Okuno

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

4 Citations (Scopus)

Abstract

The sequence of strings played on a bowed string instrument is essential to understanding of the fingering. Thus, its estimation is required for machine understanding of violin playing. Audio-based identification is the only viable way to realize this goal for existing music recordings. A naïve implementation using audio classification alone, however, is inaccurate and is not robust against variations in string or instruments. We develop a bowed string sequence estimation method by combining audio-based bowed string classification and context-dependent error correction. The robustness against different setups of instruments improves by normalizing the F0-dependent features using the average feature of a recording. The performance of error correction is evaluated using an electric violin with two different brands of strings and and an acoustic violin. By incorporating mean normalization, the recognition error of recognition accuracy due to changing the string alleviates by 8 points, and that due to change of instrument by 12 points. Error correction decreases the error due to change of string by 8 points and that due to different instrument by 9 points.

Original languageEnglish
Title of host publicationISM 2009 - 11th IEEE International Symposium on Multimedia
Pages9-16
Number of pages8
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event11th IEEE International Symposium on Multimedia, ISM 2009 - San Diego, CA
Duration: 2009 Dec 142009 Dec 16

Other

Other11th IEEE International Symposium on Multimedia, ISM 2009
CitySan Diego, CA
Period09/12/1409/12/16

Fingerprint

Error correction
Acoustics

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Maezawa, A., Itoyama, K., Takahashi, T., Ogata, T., & Okuno, H. G. (2009). Bowed string sequence estimation of a violin based on adaptive audio signal classification and context-dependent error correction. In ISM 2009 - 11th IEEE International Symposium on Multimedia (pp. 9-16). [5365381] https://doi.org/10.1109/ISM.2009.30

Bowed string sequence estimation of a violin based on adaptive audio signal classification and context-dependent error correction. / Maezawa, Akira; Itoyama, Katsutoshi; Takahashi, Toru; Ogata, Tetsuya; Okuno, Hiroshi G.

ISM 2009 - 11th IEEE International Symposium on Multimedia. 2009. p. 9-16 5365381.

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

Maezawa, A, Itoyama, K, Takahashi, T, Ogata, T & Okuno, HG 2009, Bowed string sequence estimation of a violin based on adaptive audio signal classification and context-dependent error correction. in ISM 2009 - 11th IEEE International Symposium on Multimedia., 5365381, pp. 9-16, 11th IEEE International Symposium on Multimedia, ISM 2009, San Diego, CA, 09/12/14. https://doi.org/10.1109/ISM.2009.30
Maezawa A, Itoyama K, Takahashi T, Ogata T, Okuno HG. Bowed string sequence estimation of a violin based on adaptive audio signal classification and context-dependent error correction. In ISM 2009 - 11th IEEE International Symposium on Multimedia. 2009. p. 9-16. 5365381 https://doi.org/10.1109/ISM.2009.30
Maezawa, Akira ; Itoyama, Katsutoshi ; Takahashi, Toru ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Bowed string sequence estimation of a violin based on adaptive audio signal classification and context-dependent error correction. ISM 2009 - 11th IEEE International Symposium on Multimedia. 2009. pp. 9-16
@inproceedings{d1709d99a5ef4e519bfb420a1bd974c7,
title = "Bowed string sequence estimation of a violin based on adaptive audio signal classification and context-dependent error correction",
abstract = "The sequence of strings played on a bowed string instrument is essential to understanding of the fingering. Thus, its estimation is required for machine understanding of violin playing. Audio-based identification is the only viable way to realize this goal for existing music recordings. A na{\"i}ve implementation using audio classification alone, however, is inaccurate and is not robust against variations in string or instruments. We develop a bowed string sequence estimation method by combining audio-based bowed string classification and context-dependent error correction. The robustness against different setups of instruments improves by normalizing the F0-dependent features using the average feature of a recording. The performance of error correction is evaluated using an electric violin with two different brands of strings and and an acoustic violin. By incorporating mean normalization, the recognition error of recognition accuracy due to changing the string alleviates by 8 points, and that due to change of instrument by 12 points. Error correction decreases the error due to change of string by 8 points and that due to different instrument by 9 points.",
author = "Akira Maezawa and Katsutoshi Itoyama and Toru Takahashi and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2009",
doi = "10.1109/ISM.2009.30",
language = "English",
isbn = "9780769538907",
pages = "9--16",
booktitle = "ISM 2009 - 11th IEEE International Symposium on Multimedia",

}

TY - GEN

T1 - Bowed string sequence estimation of a violin based on adaptive audio signal classification and context-dependent error correction

AU - Maezawa, Akira

AU - Itoyama, Katsutoshi

AU - Takahashi, Toru

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2009

Y1 - 2009

N2 - The sequence of strings played on a bowed string instrument is essential to understanding of the fingering. Thus, its estimation is required for machine understanding of violin playing. Audio-based identification is the only viable way to realize this goal for existing music recordings. A naïve implementation using audio classification alone, however, is inaccurate and is not robust against variations in string or instruments. We develop a bowed string sequence estimation method by combining audio-based bowed string classification and context-dependent error correction. The robustness against different setups of instruments improves by normalizing the F0-dependent features using the average feature of a recording. The performance of error correction is evaluated using an electric violin with two different brands of strings and and an acoustic violin. By incorporating mean normalization, the recognition error of recognition accuracy due to changing the string alleviates by 8 points, and that due to change of instrument by 12 points. Error correction decreases the error due to change of string by 8 points and that due to different instrument by 9 points.

AB - The sequence of strings played on a bowed string instrument is essential to understanding of the fingering. Thus, its estimation is required for machine understanding of violin playing. Audio-based identification is the only viable way to realize this goal for existing music recordings. A naïve implementation using audio classification alone, however, is inaccurate and is not robust against variations in string or instruments. We develop a bowed string sequence estimation method by combining audio-based bowed string classification and context-dependent error correction. The robustness against different setups of instruments improves by normalizing the F0-dependent features using the average feature of a recording. The performance of error correction is evaluated using an electric violin with two different brands of strings and and an acoustic violin. By incorporating mean normalization, the recognition error of recognition accuracy due to changing the string alleviates by 8 points, and that due to change of instrument by 12 points. Error correction decreases the error due to change of string by 8 points and that due to different instrument by 9 points.

UR - http://www.scopus.com/inward/record.url?scp=77949613957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949613957&partnerID=8YFLogxK

U2 - 10.1109/ISM.2009.30

DO - 10.1109/ISM.2009.30

M3 - Conference contribution

SN - 9780769538907

SP - 9

EP - 16

BT - ISM 2009 - 11th IEEE International Symposium on Multimedia

ER -