Advanced search

A probabilistic framework for audio-based tonal key and chord recognition

Benoit Catteau (UGent) , Jean-Pierre Martens (UGent) and Marc Leman (UGent)
Author
Organization
Abstract
A unified probabilistic framework for audio-based chord and tonal key recognition is described and evaluated. The proposed framework embodies an acoustic observation likelihood model and key & chord transition models. It is shown how to conceive these models and how to use music theory to link key/chord transition probabilities to perceptual similarities between keys/chords. The advantage of a theory based model is that it does not require any training, and consequently, that its performance is not affected by the quality of the available training data.
Keywords
ALGORITHM

Citation

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

Chicago
Catteau, Benoit, Jean-Pierre Martens, and Marc Leman. 2007. “A Probabilistic Framework for Audio-based Tonal Key and Chord Recognition.” In Studies in Classification, Data Analysis, and Knowledge Organization, ed. R Decker and HJ Lenz, 637–644. Berlin, Germany: Springer.
APA
Catteau, B., Martens, J.-P., & Leman, M. (2007). A probabilistic framework for audio-based tonal key and chord recognition. In R. Decker & H. Lenz (Eds.), STUDIES IN CLASSIFICATION, DATA ANALYSIS, AND KNOWLEDGE ORGANIZATION (pp. 637–644). Presented at the 30th Annual Conference of the German-Classification-Society, Berlin, Germany: Springer.
Vancouver
1.
Catteau B, Martens J-P, Leman M. A probabilistic framework for audio-based tonal key and chord recognition. In: Decker R, Lenz H, editors. STUDIES IN CLASSIFICATION, DATA ANALYSIS, AND KNOWLEDGE ORGANIZATION. Berlin, Germany: Springer; 2007. p. 637–44.
MLA
Catteau, Benoit, Jean-Pierre Martens, and Marc Leman. “A Probabilistic Framework for Audio-based Tonal Key and Chord Recognition.” Studies in Classification, Data Analysis, and Knowledge Organization. Ed. R Decker & HJ Lenz. Berlin, Germany: Springer, 2007. 637–644. Print.
@inproceedings{386772,
  abstract     = {A unified probabilistic framework for audio-based chord and tonal key recognition is described and evaluated. The proposed framework embodies an acoustic observation likelihood model and key \& chord transition models. It is shown how to conceive these models and how to use music theory to link key/chord transition probabilities to perceptual similarities between keys/chords. The advantage of a theory based model is that it does not require any training, and consequently, that its performance is not affected by the quality of the available training data.},
  author       = {Catteau, Benoit and Martens, Jean-Pierre and Leman, Marc},
  booktitle    = {STUDIES IN CLASSIFICATION, DATA ANALYSIS, AND KNOWLEDGE ORGANIZATION},
  editor       = {Decker, R and Lenz, HJ},
  isbn         = {9783540709800},
  issn         = {1431-8814},
  keyword      = {ALGORITHM},
  language     = {eng},
  location     = {Berlin, Germany},
  pages        = {637--644},
  publisher    = {Springer},
  title        = {A probabilistic framework for audio-based tonal key and chord recognition},
  year         = {2007},
}

Web of Science
Times cited: