Ghent University Academic Bibliography

Advanced

A robust audio fingerprinter based on pitch class histograms: applications for ethnic music archives

Joren Six UGent and Olmo Cornelis UGent (2012) International Workshop of Folk Music Analysis, Proceedings.
abstract
In this paper we present a new acoustic fingerprinting system, based on pitch class histograms. The aim of acoustic fingerprinting is to generate a small representation of an audio signal that can be used to identify identical, or recognize similar, audio snippets in a large audio set. A robust fingerprint generates similar fingerprints for perceptually similar audio signals. A piece of music with a noise added should generate an almost identical fingerprint as the original. The new system, presented here, has some interesting features which makes it a valuable tool to manage ethnic music archives: the fingerprints are rather robust against pitch shift, tempo changes, several synthetic audio effects, and reversal of the audio. To some degree, the system even keeps working when only part of the audio is used to generate the fingerprint.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
in
International Workshop of Folk Music Analysis, Proceedings
pages
7 pages
publisher
Ghent University, Department of Art, music and theatre sciences
place of publication
Ghent, Belgium
conference name
International Workshop of Folk Music Analysis (FMA - 2012)
conference location
Sevilla, Spanje
conference start
2012-04-19
conference end
2012-04-21
language
English
UGent publication?
yes
classification
C1
copyright statement
I have transferred the copyright for this publication to the publisher
id
3009314
handle
http://hdl.handle.net/1854/LU-3009314
date created
2012-10-09 09:00:37
date last changed
2014-02-07 13:12:47
@inproceedings{3009314,
  abstract     = {In this paper we present a new acoustic fingerprinting system, based on pitch class histograms. The aim of acoustic fingerprinting is to generate a small representation of an audio signal that can be used to identify identical, or recognize similar, audio snippets in a large audio set. A robust fingerprint generates similar fingerprints for perceptually similar audio signals. A piece of music with a noise added should generate an almost identical fingerprint as the original. The new system, presented here, has some interesting features which makes it a valuable tool to manage ethnic music archives: the fingerprints are rather robust against pitch shift, tempo changes, several synthetic audio effects, and reversal of the audio. To some degree, the system even keeps working when only part of the audio is used to generate the fingerprint.},
  author       = {Six, Joren and Cornelis, Olmo},
  booktitle    = {International Workshop of Folk Music Analysis, Proceedings},
  language     = {eng},
  location     = {Sevilla, Spanje},
  pages        = {7},
  publisher    = {Ghent University, Department of Art, music and theatre sciences},
  title        = {A robust audio fingerprinter based on pitch class histograms: applications for ethnic music archives},
  year         = {2012},
}

Chicago
Six, Joren, and Olmo Cornelis. 2012. “A Robust Audio Fingerprinter Based on Pitch Class Histograms: Applications for Ethnic Music Archives.” In International Workshop of Folk Music Analysis, Proceedings. Ghent, Belgium: Ghent University, Department of Art, music and theatre sciences.
APA
Six, J., & Cornelis, O. (2012). A robust audio fingerprinter based on pitch class histograms: applications for ethnic music archives. International Workshop of Folk Music Analysis, Proceedings. Presented at the International Workshop of Folk Music Analysis (FMA - 2012), Ghent, Belgium: Ghent University, Department of Art, music and theatre sciences.
Vancouver
1.
Six J, Cornelis O. A robust audio fingerprinter based on pitch class histograms: applications for ethnic music archives. International Workshop of Folk Music Analysis, Proceedings. Ghent, Belgium: Ghent University, Department of Art, music and theatre sciences; 2012.
MLA
Six, Joren, and Olmo Cornelis. “A Robust Audio Fingerprinter Based on Pitch Class Histograms: Applications for Ethnic Music Archives.” International Workshop of Folk Music Analysis, Proceedings. Ghent, Belgium: Ghent University, Department of Art, music and theatre sciences, 2012. Print.