Ghent University Academic Bibliography

Advanced

The influence of chord duration modeling on chord and local key extraction

Johan Pauwels UGent, Jean-Pierre Martens UGent and Marc Leman UGent (2011) International Conference on Machine Learning and Applications, Proceedings. p.136-141
abstract
In this paper, we investigate the effect of different types of chord duration modeling on the performance of a simultaneous chord and local key extraction system. Two hypotheses are examined, (1) whether the introduction of multiple states per key-chord combination makes any difference as it changes the prior duration from a geometric distribution to a negative binomial distribution, and (2) whether making the prior mean duration of a key-chord combination a function of the chord has a positive effect. We found that the introduction of multiple states per key-chord has no influence on neither key nor chord extraction performance, but making the mean duration a function of the chord interpreted in its key leads to an increase in the key estimation capabilities.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
music information retrieval, duration modeling, key extraction, chord extraction
in
International Conference on Machine Learning and Applications, Proceedings
pages
136 - 141
publisher
IEEE
place of publication
Piscataway, NJ, USA
conference name
Tenth International Conference on Machine Learning and Applications (ICMLA 2011)
conference location
Honolulu, Hawaï, USA
conference start
2011-12-18
conference end
2011-12-21
ISBN
9780769546070
DOI
10.1109/ICMLA.2011.141
project
GOA-1250604
language
English
UGent publication?
yes
classification
C1
copyright statement
I have transferred the copyright for this publication to the publisher
id
1977558
handle
http://hdl.handle.net/1854/LU-1977558
date created
2012-01-03 18:42:29
date last changed
2015-06-17 09:53:36
@inproceedings{1977558,
  abstract     = {In this paper, we investigate the effect of different types of chord duration modeling on the performance of a simultaneous chord and local key extraction system. Two hypotheses are examined, (1) whether the introduction of multiple states per key-chord combination makes any difference as it changes the prior duration from a geometric distribution to a negative binomial distribution, and (2) whether making the prior mean duration of a key-chord combination a function of the chord has a positive effect. We found that the introduction of multiple states per key-chord has no influence on neither key nor chord extraction performance, but making the mean duration a function of the chord interpreted in its key leads to an increase in the key estimation capabilities.},
  author       = {Pauwels, Johan and Martens, Jean-Pierre and Leman, Marc},
  booktitle    = {International Conference on Machine Learning and Applications, Proceedings},
  isbn         = {9780769546070},
  keyword      = {music information retrieval,duration modeling,key extraction,chord extraction},
  language     = {eng},
  location     = {Honolulu, Hawa{\"i}, USA},
  pages        = {136--141},
  publisher    = {IEEE},
  title        = {The influence of chord duration modeling on chord and local key extraction},
  url          = {http://dx.doi.org/10.1109/ICMLA.2011.141},
  year         = {2011},
}

Chicago
Pauwels, Johan, Jean-Pierre Martens, and Marc Leman. 2011. “The Influence of Chord Duration Modeling on Chord and Local Key Extraction.” In International Conference on Machine Learning and Applications, Proceedings, 136–141. Piscataway, NJ, USA: IEEE.
APA
Pauwels, J., Martens, J.-P., & Leman, M. (2011). The influence of chord duration modeling on chord and local key extraction. International Conference on Machine Learning and Applications, Proceedings (pp. 136–141). Presented at the Tenth International Conference on Machine Learning and Applications (ICMLA 2011), Piscataway, NJ, USA: IEEE.
Vancouver
1.
Pauwels J, Martens J-P, Leman M. The influence of chord duration modeling on chord and local key extraction. International Conference on Machine Learning and Applications, Proceedings. Piscataway, NJ, USA: IEEE; 2011. p. 136–41.
MLA
Pauwels, Johan, Jean-Pierre Martens, and Marc Leman. “The Influence of Chord Duration Modeling on Chord and Local Key Extraction.” International Conference on Machine Learning and Applications, Proceedings. Piscataway, NJ, USA: IEEE, 2011. 136–141. Print.