%Aigaion2 BibTeX export from Idiap Publications
%Monday 29 April 2024 12:53:04 AM

@INPROCEEDINGS{paiement05art,
         author = {Paiement, Jean-Fran{\c c}ois and Eck, Douglas and Bengio, Samy and Barber, David},
       projects = {Idiap},
          title = {A Graphical Model for Chord Progressions Embedded in a Psychoacoustic Space},
      booktitle = {Proceedings of the 22nd International Conference on Machine Learning},
           year = {2005},
           note = {IDIAP-RR 05-33},
       crossref = {paiement05a},
       abstract = {Chord progressions are the building blocks from which tonal music is constructed. Inferring chord progressions is thus an essential step towards modeling long term dependencies in music. In this paper, a distributed representation for chords is designed such that Euclidean distances roughly correspond to psychoacoustic dissimilarities. Parameters in the graphical models are learnt with the EM algorithm and the classical Junction Tree algorithm. Various model architectures are compared in terms of conditional out-of-sample likelihood. Both perceptual and statistical evidence show that binary trees related to meter are well suited to capture chord dependencies.},
            pdf = {https://publications.idiap.ch/attachments/papers/2005/chords.pdf},
ipdmembership={learning},
}



crossreferenced publications: 
@TECHREPORT{paiement05a,
         author = {Paiement, Jean-Fran{\c c}ois and Eck, Douglas and Bengio, Samy and Barber, David},
       projects = {Idiap},
          title = {A Graphical Model for Chord Progressions Embedded in a Psychoacoustic Space},
           type = {Idiap-RR},
         number = {Idiap-RR-33-2005},
           year = {2005},
    institution = {IDIAP Research Institute},
           note = {Published in Proceedings of the 22nd International Conference on Machine Learning},
       abstract = {Chord progressions are the building blocks from which tonal music is constructed. Inferring chord progressions is thus an essential step towards modeling long term dependencies in music. In this paper, a distributed representation for chords is designed such that Euclidean distances roughly correspond to psychoacoustic dissimilarities. Parameters in the graphical models are learnt with the EM algorithm and the classical Junction Tree algorithm. Various model architectures are compared in terms of conditional out-of-sample likelihood. Both perceptual and statistical evidence show that binary trees related to meter are well suited to capture chord dependencies.},
            pdf = {https://publications.idiap.ch/attachments/reports/2005/rr_icml.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2005/rr_icml.ps.gz},
ipdmembership={learning},
}