Melody harmonisation with interpolated probabilistic models

Stanislaw Raczynski 1, 2 Satoru Fukayama 3 Emmanuel Vincent 1, 4
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
4 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Most melody harmonisation systems use the generative hidden Markov model (HMM), which model the relation between the hidden chords and the observed melody. Relations to other variables, such as the tonality or the metric struc- ture, are handled by training multiple HMMs or are ignored. In this paper, we propose a discriminative means of combining multiple probabilistic models of various musical variables by means of model interpolation. We evaluate our models in terms of their cross-entropy and their performance in harmonisation experiments. The proposed model o ered higher chord root accuracy than the reference musicological rule-based harmoniser by up to 5% absolute.
Type de document :
Article dans une revue
Journal of New Music Research, Taylor & Francis (Routledge), 2013, 42 (3), pp.223-235. 〈10.1080/09298215.2013.822000〉
Liste complète des métadonnées
Contributeur : Emmanuel Vincent <>
Soumis le : mercredi 23 octobre 2013 - 17:24:26
Dernière modification le : jeudi 11 janvier 2018 - 06:25:24



Stanislaw Raczynski, Satoru Fukayama, Emmanuel Vincent. Melody harmonisation with interpolated probabilistic models. Journal of New Music Research, Taylor & Francis (Routledge), 2013, 42 (3), pp.223-235. 〈10.1080/09298215.2013.822000〉. 〈hal-00876128〉



Consultations de la notice