Towards the characterization of singing styles in world music

Maria Panteli, Rachel Bittner, Juan Bello, Simon Dixon

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

Abstract

In this paper we focus on the characterization of singing styles in world music. We develop a set of contour features capturing pitch structure and melodic embellishments. Using these features we train a binary classifier to distinguish vocal from non-vocal contours and learn a dictionary of singing style elements. Each contour is mapped to the dictionary elements and each recording is summarized as the histogram of its contour mappings. We use K-means clustering on the recording representations as a proxy for singing style similarity. We observe clusters distinguished by characteristic uses of singing techniques such as vibrato and melisma. Recordings that are clustered together are often from neighbouring countries or exhibit aspects of language and cultural proximity. Studying singing particularities in this comparative manner can contribute to understanding the interaction and exchange between world music styles.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages636-640
Number of pages5
ISBN (Electronic)9781509041176
DOIs
StatePublished - Jun 16 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: Mar 5 2017Mar 9 2017

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period3/5/173/9/17

Fingerprint

Glossaries
Classifiers

Keywords

  • features
  • pitch
  • singing
  • unsupervised learning
  • world music

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Panteli, M., Bittner, R., Bello, J., & Dixon, S. (2017). Towards the characterization of singing styles in world music. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 636-640). [7952233] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952233

Towards the characterization of singing styles in world music. / Panteli, Maria; Bittner, Rachel; Bello, Juan; Dixon, Simon.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 636-640 7952233.

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

Panteli, M, Bittner, R, Bello, J & Dixon, S 2017, Towards the characterization of singing styles in world music. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952233, Institute of Electrical and Electronics Engineers Inc., pp. 636-640, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 3/5/17. https://doi.org/10.1109/ICASSP.2017.7952233
Panteli M, Bittner R, Bello J, Dixon S. Towards the characterization of singing styles in world music. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 636-640. 7952233 https://doi.org/10.1109/ICASSP.2017.7952233
Panteli, Maria ; Bittner, Rachel ; Bello, Juan ; Dixon, Simon. / Towards the characterization of singing styles in world music. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 636-640
@inproceedings{d930c9b36d734ae4bbd1d69ec9c70603,
title = "Towards the characterization of singing styles in world music",
abstract = "In this paper we focus on the characterization of singing styles in world music. We develop a set of contour features capturing pitch structure and melodic embellishments. Using these features we train a binary classifier to distinguish vocal from non-vocal contours and learn a dictionary of singing style elements. Each contour is mapped to the dictionary elements and each recording is summarized as the histogram of its contour mappings. We use K-means clustering on the recording representations as a proxy for singing style similarity. We observe clusters distinguished by characteristic uses of singing techniques such as vibrato and melisma. Recordings that are clustered together are often from neighbouring countries or exhibit aspects of language and cultural proximity. Studying singing particularities in this comparative manner can contribute to understanding the interaction and exchange between world music styles.",
keywords = "features, pitch, singing, unsupervised learning, world music",
author = "Maria Panteli and Rachel Bittner and Juan Bello and Simon Dixon",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/ICASSP.2017.7952233",
language = "English (US)",
pages = "636--640",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Towards the characterization of singing styles in world music

AU - Panteli, Maria

AU - Bittner, Rachel

AU - Bello, Juan

AU - Dixon, Simon

PY - 2017/6/16

Y1 - 2017/6/16

N2 - In this paper we focus on the characterization of singing styles in world music. We develop a set of contour features capturing pitch structure and melodic embellishments. Using these features we train a binary classifier to distinguish vocal from non-vocal contours and learn a dictionary of singing style elements. Each contour is mapped to the dictionary elements and each recording is summarized as the histogram of its contour mappings. We use K-means clustering on the recording representations as a proxy for singing style similarity. We observe clusters distinguished by characteristic uses of singing techniques such as vibrato and melisma. Recordings that are clustered together are often from neighbouring countries or exhibit aspects of language and cultural proximity. Studying singing particularities in this comparative manner can contribute to understanding the interaction and exchange between world music styles.

AB - In this paper we focus on the characterization of singing styles in world music. We develop a set of contour features capturing pitch structure and melodic embellishments. Using these features we train a binary classifier to distinguish vocal from non-vocal contours and learn a dictionary of singing style elements. Each contour is mapped to the dictionary elements and each recording is summarized as the histogram of its contour mappings. We use K-means clustering on the recording representations as a proxy for singing style similarity. We observe clusters distinguished by characteristic uses of singing techniques such as vibrato and melisma. Recordings that are clustered together are often from neighbouring countries or exhibit aspects of language and cultural proximity. Studying singing particularities in this comparative manner can contribute to understanding the interaction and exchange between world music styles.

KW - features

KW - pitch

KW - singing

KW - unsupervised learning

KW - world music

UR - http://www.scopus.com/inward/record.url?scp=85023756611&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023756611&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952233

DO - 10.1109/ICASSP.2017.7952233

M3 - Conference contribution

AN - SCOPUS:85023756611

SP - 636

EP - 640

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -