Pitch contours as a mid-level representation for music informatics

Rachel M. Bittner, Justin Salamon, Juan J. Bosch, Juan Bello

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

Abstract

Content-based Music Informatics includes tasks that involve estimating the pitched content of music, such as the main melody or the bass line. To date, the field lacks a good machine representation that models the human perception of pitch, with each task using specific, tailored representations. This paper proposes factoring pitch estimation problems into two stages, where the output of the first stage for all tasks is a multipitch contour representation. Further, we propose the adoption of pitch contours as a unit of pitch organization. We give a review of the existing work on contour extraction and characterization and present experiments that demonstrate the discriminability of pitch contours.

Original languageEnglish (US)
Title of host publicationProceedings of the 2017 AES International Conference
Subtitle of host publicationSemantic Audio
PublisherAudio Engineering Society
Pages100-107
Number of pages8
Volume22-24-June-2017
StatePublished - 2017
Event3rd AES International Conference on Semantic Audio 2017 - Erlangen, Germany
Duration: Jun 22 2017Jun 24 2017

Other

Other3rd AES International Conference on Semantic Audio 2017
CountryGermany
CityErlangen
Period6/22/176/24/17

Fingerprint

music
Experiments
estimating
output

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Bittner, R. M., Salamon, J., Bosch, J. J., & Bello, J. (2017). Pitch contours as a mid-level representation for music informatics. In Proceedings of the 2017 AES International Conference: Semantic Audio (Vol. 22-24-June-2017, pp. 100-107). Audio Engineering Society.

Pitch contours as a mid-level representation for music informatics. / Bittner, Rachel M.; Salamon, Justin; Bosch, Juan J.; Bello, Juan.

Proceedings of the 2017 AES International Conference: Semantic Audio. Vol. 22-24-June-2017 Audio Engineering Society, 2017. p. 100-107.

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

Bittner, RM, Salamon, J, Bosch, JJ & Bello, J 2017, Pitch contours as a mid-level representation for music informatics. in Proceedings of the 2017 AES International Conference: Semantic Audio. vol. 22-24-June-2017, Audio Engineering Society, pp. 100-107, 3rd AES International Conference on Semantic Audio 2017, Erlangen, Germany, 6/22/17.
Bittner RM, Salamon J, Bosch JJ, Bello J. Pitch contours as a mid-level representation for music informatics. In Proceedings of the 2017 AES International Conference: Semantic Audio. Vol. 22-24-June-2017. Audio Engineering Society. 2017. p. 100-107
Bittner, Rachel M. ; Salamon, Justin ; Bosch, Juan J. ; Bello, Juan. / Pitch contours as a mid-level representation for music informatics. Proceedings of the 2017 AES International Conference: Semantic Audio. Vol. 22-24-June-2017 Audio Engineering Society, 2017. pp. 100-107
@inproceedings{abb0add19b04495bb6a364ba9294d1c0,
title = "Pitch contours as a mid-level representation for music informatics",
abstract = "Content-based Music Informatics includes tasks that involve estimating the pitched content of music, such as the main melody or the bass line. To date, the field lacks a good machine representation that models the human perception of pitch, with each task using specific, tailored representations. This paper proposes factoring pitch estimation problems into two stages, where the output of the first stage for all tasks is a multipitch contour representation. Further, we propose the adoption of pitch contours as a unit of pitch organization. We give a review of the existing work on contour extraction and characterization and present experiments that demonstrate the discriminability of pitch contours.",
author = "Bittner, {Rachel M.} and Justin Salamon and Bosch, {Juan J.} and Juan Bello",
year = "2017",
language = "English (US)",
volume = "22-24-June-2017",
pages = "100--107",
booktitle = "Proceedings of the 2017 AES International Conference",
publisher = "Audio Engineering Society",
address = "United States",

}

TY - GEN

T1 - Pitch contours as a mid-level representation for music informatics

AU - Bittner, Rachel M.

AU - Salamon, Justin

AU - Bosch, Juan J.

AU - Bello, Juan

PY - 2017

Y1 - 2017

N2 - Content-based Music Informatics includes tasks that involve estimating the pitched content of music, such as the main melody or the bass line. To date, the field lacks a good machine representation that models the human perception of pitch, with each task using specific, tailored representations. This paper proposes factoring pitch estimation problems into two stages, where the output of the first stage for all tasks is a multipitch contour representation. Further, we propose the adoption of pitch contours as a unit of pitch organization. We give a review of the existing work on contour extraction and characterization and present experiments that demonstrate the discriminability of pitch contours.

AB - Content-based Music Informatics includes tasks that involve estimating the pitched content of music, such as the main melody or the bass line. To date, the field lacks a good machine representation that models the human perception of pitch, with each task using specific, tailored representations. This paper proposes factoring pitch estimation problems into two stages, where the output of the first stage for all tasks is a multipitch contour representation. Further, we propose the adoption of pitch contours as a unit of pitch organization. We give a review of the existing work on contour extraction and characterization and present experiments that demonstrate the discriminability of pitch contours.

UR - http://www.scopus.com/inward/record.url?scp=85028074926&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028074926&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85028074926

VL - 22-24-June-2017

SP - 100

EP - 107

BT - Proceedings of the 2017 AES International Conference

PB - Audio Engineering Society

ER -