A temporal multi-view approach for audio key finding using adaboost

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

Abstract

Audio key finding is an integral step in content-based music indexing and retrieval. In this paper, we present a system that combines ensemble learning with an existing model-based key finding algorithm: the Fuzzy Analysis Center of Effect Generator algorithm. We demonstrate the manner in which AdaBoost improves the accuracy of FACEG using a dataset containing 2785 audio excerpts of real performances composed by Bach and Mozart. Two sets of experiments were conducted: intra-system comparison examining the effect of different settings in FACEG/AdaBoost, and inter-system comparison comparing FACEG/AdaBoost with the key finding implementation in Music Information Retrieval (MIR) toolbox. When FACEG is executed to generate keys at multiple stopping points of the excerpt, AdaBoost with multi-views of tonal information improves key detection accuracy up to 35% on the challenging dataset and up to 21% on the entire dataset.

Original languageEnglish (US)
Title of host publicationElectronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013
DOIs
StatePublished - Nov 29 2013
Externally publishedYes
Event2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013 - San Jose, CA, United States
Duration: Jul 15 2013Jul 19 2013

Other

Other2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013
CountryUnited States
CitySan Jose, CA
Period7/15/137/19/13

Fingerprint

Adaptive boosting
Information retrieval
Experiments

Keywords

  • AdaBoost
  • Audio key finding
  • Center of Effect Generator
  • Fuzzy Analysis
  • Spiral Array

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Chuan, C-H. (2013). A temporal multi-view approach for audio key finding using adaboost. In Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013 [6618295] https://doi.org/10.1109/ICMEW.2013.6618295

A temporal multi-view approach for audio key finding using adaboost. / Chuan, Ching-Hua.

Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013. 2013. 6618295.

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

Chuan, C-H 2013, A temporal multi-view approach for audio key finding using adaboost. in Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013., 6618295, 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013, San Jose, CA, United States, 7/15/13. https://doi.org/10.1109/ICMEW.2013.6618295
Chuan C-H. A temporal multi-view approach for audio key finding using adaboost. In Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013. 2013. 6618295 https://doi.org/10.1109/ICMEW.2013.6618295
Chuan, Ching-Hua. / A temporal multi-view approach for audio key finding using adaboost. Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013. 2013.
@inproceedings{c6aa342668da45b6b9421dbe2be5b73c,
title = "A temporal multi-view approach for audio key finding using adaboost",
abstract = "Audio key finding is an integral step in content-based music indexing and retrieval. In this paper, we present a system that combines ensemble learning with an existing model-based key finding algorithm: the Fuzzy Analysis Center of Effect Generator algorithm. We demonstrate the manner in which AdaBoost improves the accuracy of FACEG using a dataset containing 2785 audio excerpts of real performances composed by Bach and Mozart. Two sets of experiments were conducted: intra-system comparison examining the effect of different settings in FACEG/AdaBoost, and inter-system comparison comparing FACEG/AdaBoost with the key finding implementation in Music Information Retrieval (MIR) toolbox. When FACEG is executed to generate keys at multiple stopping points of the excerpt, AdaBoost with multi-views of tonal information improves key detection accuracy up to 35{\%} on the challenging dataset and up to 21{\%} on the entire dataset.",
keywords = "AdaBoost, Audio key finding, Center of Effect Generator, Fuzzy Analysis, Spiral Array",
author = "Ching-Hua Chuan",
year = "2013",
month = "11",
day = "29",
doi = "10.1109/ICMEW.2013.6618295",
language = "English (US)",
isbn = "9781479916047",
booktitle = "Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013",

}

TY - GEN

T1 - A temporal multi-view approach for audio key finding using adaboost

AU - Chuan, Ching-Hua

PY - 2013/11/29

Y1 - 2013/11/29

N2 - Audio key finding is an integral step in content-based music indexing and retrieval. In this paper, we present a system that combines ensemble learning with an existing model-based key finding algorithm: the Fuzzy Analysis Center of Effect Generator algorithm. We demonstrate the manner in which AdaBoost improves the accuracy of FACEG using a dataset containing 2785 audio excerpts of real performances composed by Bach and Mozart. Two sets of experiments were conducted: intra-system comparison examining the effect of different settings in FACEG/AdaBoost, and inter-system comparison comparing FACEG/AdaBoost with the key finding implementation in Music Information Retrieval (MIR) toolbox. When FACEG is executed to generate keys at multiple stopping points of the excerpt, AdaBoost with multi-views of tonal information improves key detection accuracy up to 35% on the challenging dataset and up to 21% on the entire dataset.

AB - Audio key finding is an integral step in content-based music indexing and retrieval. In this paper, we present a system that combines ensemble learning with an existing model-based key finding algorithm: the Fuzzy Analysis Center of Effect Generator algorithm. We demonstrate the manner in which AdaBoost improves the accuracy of FACEG using a dataset containing 2785 audio excerpts of real performances composed by Bach and Mozart. Two sets of experiments were conducted: intra-system comparison examining the effect of different settings in FACEG/AdaBoost, and inter-system comparison comparing FACEG/AdaBoost with the key finding implementation in Music Information Retrieval (MIR) toolbox. When FACEG is executed to generate keys at multiple stopping points of the excerpt, AdaBoost with multi-views of tonal information improves key detection accuracy up to 35% on the challenging dataset and up to 21% on the entire dataset.

KW - AdaBoost

KW - Audio key finding

KW - Center of Effect Generator

KW - Fuzzy Analysis

KW - Spiral Array

UR - http://www.scopus.com/inward/record.url?scp=84888251068&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888251068&partnerID=8YFLogxK

U2 - 10.1109/ICMEW.2013.6618295

DO - 10.1109/ICMEW.2013.6618295

M3 - Conference contribution

SN - 9781479916047

BT - Electronic Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2013

ER -