Audio-based guitar tablature transcription using multipitch analysis and playability constraints

Kazuki Yazawa, Daichi Sakaue, Kohei Nagira, Katsutoshi Itoyama, Hiroshi G. Okuno

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

7 Citations (Scopus)

Abstract

This paper proposes a method of guitar tablature transcription from audio signals. Multipitch estimation and fingering configuration estimation are essential for transcribing tablatures. Conventional multipitch estimation methods, including latent harmonic allocation (LHA), often estimate combinations of pitches that people cannot play due to inherent physical constraints. Unplayable combinations of pitches are eliminated by filtering the results of LHA with three constraints. We first enumerate playable fingering configurations, and use them to suppress any undesirable combination of pitches. The optimal fingering configuration in each time frame is optimized to satisfy the need for temporal continuity by using dynamic programming. We use synthesized guitar sounds from MIDI data (ground truth) for evaluation. Experiments with them demonstrate the improvement of multipitch estimation by 5.9 points on average in F-measure and the transcribed tablatures are playable.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages196-200
Number of pages5
DOIs
Publication statusPublished - 2013 Oct 18
Externally publishedYes
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC
Duration: 2013 May 262013 May 31

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CityVancouver, BC
Period13/5/2613/5/31

Fingerprint

Transcription
Dynamic programming
Acoustic waves
Experiments

Keywords

  • fingering configuration
  • guitar tablature
  • multipitch estimation
  • music signal processing
  • onset detection

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Yazawa, K., Sakaue, D., Nagira, K., Itoyama, K., & Okuno, H. G. (2013). Audio-based guitar tablature transcription using multipitch analysis and playability constraints. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 196-200). [6637636] https://doi.org/10.1109/ICASSP.2013.6637636

Audio-based guitar tablature transcription using multipitch analysis and playability constraints. / Yazawa, Kazuki; Sakaue, Daichi; Nagira, Kohei; Itoyama, Katsutoshi; Okuno, Hiroshi G.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 196-200 6637636.

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

Yazawa, K, Sakaue, D, Nagira, K, Itoyama, K & Okuno, HG 2013, Audio-based guitar tablature transcription using multipitch analysis and playability constraints. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6637636, pp. 196-200, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, 13/5/26. https://doi.org/10.1109/ICASSP.2013.6637636
Yazawa K, Sakaue D, Nagira K, Itoyama K, Okuno HG. Audio-based guitar tablature transcription using multipitch analysis and playability constraints. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 196-200. 6637636 https://doi.org/10.1109/ICASSP.2013.6637636
Yazawa, Kazuki ; Sakaue, Daichi ; Nagira, Kohei ; Itoyama, Katsutoshi ; Okuno, Hiroshi G. / Audio-based guitar tablature transcription using multipitch analysis and playability constraints. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. pp. 196-200
@inproceedings{00bc1b3c742c4e09a6d1a61ba5d4f722,
title = "Audio-based guitar tablature transcription using multipitch analysis and playability constraints",
abstract = "This paper proposes a method of guitar tablature transcription from audio signals. Multipitch estimation and fingering configuration estimation are essential for transcribing tablatures. Conventional multipitch estimation methods, including latent harmonic allocation (LHA), often estimate combinations of pitches that people cannot play due to inherent physical constraints. Unplayable combinations of pitches are eliminated by filtering the results of LHA with three constraints. We first enumerate playable fingering configurations, and use them to suppress any undesirable combination of pitches. The optimal fingering configuration in each time frame is optimized to satisfy the need for temporal continuity by using dynamic programming. We use synthesized guitar sounds from MIDI data (ground truth) for evaluation. Experiments with them demonstrate the improvement of multipitch estimation by 5.9 points on average in F-measure and the transcribed tablatures are playable.",
keywords = "fingering configuration, guitar tablature, multipitch estimation, music signal processing, onset detection",
author = "Kazuki Yazawa and Daichi Sakaue and Kohei Nagira and Katsutoshi Itoyama and Okuno, {Hiroshi G.}",
year = "2013",
month = "10",
day = "18",
doi = "10.1109/ICASSP.2013.6637636",
language = "English",
isbn = "9781479903566",
pages = "196--200",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Audio-based guitar tablature transcription using multipitch analysis and playability constraints

AU - Yazawa, Kazuki

AU - Sakaue, Daichi

AU - Nagira, Kohei

AU - Itoyama, Katsutoshi

AU - Okuno, Hiroshi G.

PY - 2013/10/18

Y1 - 2013/10/18

N2 - This paper proposes a method of guitar tablature transcription from audio signals. Multipitch estimation and fingering configuration estimation are essential for transcribing tablatures. Conventional multipitch estimation methods, including latent harmonic allocation (LHA), often estimate combinations of pitches that people cannot play due to inherent physical constraints. Unplayable combinations of pitches are eliminated by filtering the results of LHA with three constraints. We first enumerate playable fingering configurations, and use them to suppress any undesirable combination of pitches. The optimal fingering configuration in each time frame is optimized to satisfy the need for temporal continuity by using dynamic programming. We use synthesized guitar sounds from MIDI data (ground truth) for evaluation. Experiments with them demonstrate the improvement of multipitch estimation by 5.9 points on average in F-measure and the transcribed tablatures are playable.

AB - This paper proposes a method of guitar tablature transcription from audio signals. Multipitch estimation and fingering configuration estimation are essential for transcribing tablatures. Conventional multipitch estimation methods, including latent harmonic allocation (LHA), often estimate combinations of pitches that people cannot play due to inherent physical constraints. Unplayable combinations of pitches are eliminated by filtering the results of LHA with three constraints. We first enumerate playable fingering configurations, and use them to suppress any undesirable combination of pitches. The optimal fingering configuration in each time frame is optimized to satisfy the need for temporal continuity by using dynamic programming. We use synthesized guitar sounds from MIDI data (ground truth) for evaluation. Experiments with them demonstrate the improvement of multipitch estimation by 5.9 points on average in F-measure and the transcribed tablatures are playable.

KW - fingering configuration

KW - guitar tablature

KW - multipitch estimation

KW - music signal processing

KW - onset detection

UR - http://www.scopus.com/inward/record.url?scp=84890537974&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890537974&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2013.6637636

DO - 10.1109/ICASSP.2013.6637636

M3 - Conference contribution

AN - SCOPUS:84890537974

SN - 9781479903566

SP - 196

EP - 200

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -