Advanced search
2 files | 464.15 KB

Modeling musicological information as trigrams in a system for simultaneous chord and local key extraction

Johan Pauwels (UGent) , Jean-Pierre Martens (UGent) and Marc Leman (UGent)
Author
Organization
Project
GOA-1250604
Abstract
In this paper, we discuss the introduction of a trigram musicological model in a simultaneous chord and local key extraction system. By enlarging the context of the musicological model, we hoped to achieve a higher accuracy that could justify the associated higher complexity and computational load of the search for the optimal solution. Experiments on multiple data sets have demonstrated that the trigram model has indeed a larger predictive power (a lower perplexity). This raised predictive power resulted in an improvement in the key extraction capabilities, but no improvement in chord extraction when compared to a system with a bigram musicological model.
Keywords
music information retrieval, key extraction, chord extraction, music signal processing

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 249.93 KB
  • pauwels2011mlsp-postprint.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 214.22 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Pauwels, Johan, Jean-Pierre Martens, and Marc Leman. 2011. “Modeling Musicological Information as Trigrams in a System for Simultaneous Chord and Local Key Extraction.” In 2011 IEEE International Workshop on Machine Learning for Signal Processing. New York, NY, USA: IEEE.
APA
Pauwels, Johan, Martens, J.-P., & Leman, M. (2011). Modeling musicological information as trigrams in a system for simultaneous chord and local key extraction. 2011 IEEE International workshop on machine learning for signal processing. Presented at the 2011 IEEE International workshop on Machine Learning for Signal Processing (MLSP 2011), New York, NY, USA: IEEE.
Vancouver
1.
Pauwels J, Martens J-P, Leman M. Modeling musicological information as trigrams in a system for simultaneous chord and local key extraction. 2011 IEEE International workshop on machine learning for signal processing. New York, NY, USA: IEEE; 2011.
MLA
Pauwels, Johan, Jean-Pierre Martens, and Marc Leman. “Modeling Musicological Information as Trigrams in a System for Simultaneous Chord and Local Key Extraction.” 2011 IEEE International Workshop on Machine Learning for Signal Processing. New York, NY, USA: IEEE, 2011. Print.
@inproceedings{1945124,
  abstract     = {In this paper, we discuss the introduction of a trigram musicological model in a simultaneous chord and local key extraction system. By enlarging the context of the musicological model, we hoped to achieve a higher accuracy that could justify the associated higher complexity and computational load of the search for the optimal solution. Experiments on multiple data sets have demonstrated that the trigram model has indeed a larger predictive power (a lower perplexity). This raised predictive power resulted in an improvement in the key extraction capabilities, but no improvement in chord extraction when compared to a system with a bigram musicological model.},
  author       = {Pauwels, Johan and Martens, Jean-Pierre and Leman, Marc},
  booktitle    = {2011 IEEE International workshop on machine learning for signal processing},
  isbn         = {9781457716218},
  issn         = {1551-2541},
  keyword      = {music information retrieval,key extraction,chord extraction,music signal processing},
  language     = {eng},
  location     = {Beijing, PR China},
  pages        = {6},
  publisher    = {IEEE},
  title        = {Modeling musicological information as trigrams in a system for simultaneous chord and local key extraction},
  url          = {http://dx.doi.org/10.1109/MLSP.2011.6064602},
  year         = {2011},
}

Altmetric
View in Altmetric
Web of Science
Times cited: